Skip to content

Commit 901af51

Browse files
MMathisLabCeliaBenquet
MMathisLab
and
CeliaBenquet
authored
TOC into main dir (#51)
* Add files via upload * Delete docs/_toc.yml * Update README.md * Update pyproject.toml * Update README.md * Update pyproject.toml * Update README.md * Update README.md Co-authored-by: Célia Benquet <32598028+CeliaBenquet@users.noreply.github.com> * Update _toc.yml * Update _toc.yml * Update _toc.yml * Delete docs/docs/initial_pitch.md * Create LICENSE * cleaning * more cleaning * minor reordering * Fix API generation (#53) * Fix docs API generation * Change black to yapf similar to make format * Fix errors in formating of the markdowns and docstrings * Add favicon * Add images as static images for the readme (#54) * Remove legacy note from Riccardo's code --------- Co-authored-by: Célia Benquet <32598028+CeliaBenquet@users.noreply.github.com>
1 parent 3856dcf commit 901af51

36 files changed

Lines changed: 1411 additions & 1399 deletions

‎.github/workflows/publish-book.yml‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -19,6 +19,7 @@ jobs:
1919
- name: Install dependencies
2020
run: |
2121
python -m pip install --upgrade pip
22+
python -m pip install -e .
2223
python -m pip install .[docs]
2324
pip install jupyter-book sphinxcontrib-mermaid
2425

‎.gitignore‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ __pycache__/
88

99
# Distribution / packaging
1010
.Python
11-
build/
11+
_build/
1212
develop-eggs/
1313
dist/
1414
downloads/

‎LICENSE‎

Lines changed: 201 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,201 @@
1+
Apache License
2+
Version 2.0, January 2004
3+
http://www.apache.org/licenses/
4+
5+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6+
7+
1. Definitions.
8+
9+
"License" shall mean the terms and conditions for use, reproduction,
10+
and distribution as defined by Sections 1 through 9 of this document.
11+
12+
"Licensor" shall mean the copyright owner or entity authorized by
13+
the copyright owner that is granting the License.
14+
15+
"Legal Entity" shall mean the union of the acting entity and all
16+
other entities that control, are controlled by, or are under common
17+
control with that entity. For the purposes of this definition,
18+
"control" means (i) the power, direct or indirect, to cause the
19+
direction or management of such entity, whether by contract or
20+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
21+
outstanding shares, or (iii) beneficial ownership of such entity.
22+
23+
"You" (or "Your") shall mean an individual or Legal Entity
24+
exercising permissions granted by this License.
25+
26+
"Source" form shall mean the preferred form for making modifications,
27+
including but not limited to software source code, documentation
28+
source, and configuration files.
29+
30+
"Object" form shall mean any form resulting from mechanical
31+
transformation or translation of a Source form, including but
32+
not limited to compiled object code, generated documentation,
33+
and conversions to other media types.
34+
35+
"Work" shall mean the work of authorship, whether in Source or
36+
Object form, made available under the License, as indicated by a
37+
copyright notice that is included in or attached to the work
38+
(an example is provided in the Appendix below).
39+
40+
"Derivative Works" shall mean any work, whether in Source or Object
41+
form, that is based on (or derived from) the Work and for which the
42+
editorial revisions, annotations, elaborations, or other modifications
43+
represent, as a whole, an original work of authorship. For the purposes
44+
of this License, Derivative Works shall not include works that remain
45+
separable from, or merely link (or bind by name) to the interfaces of,
46+
the Work and Derivative Works thereof.
47+
48+
"Contribution" shall mean any work of authorship, including
49+
the original version of the Work and any modifications or additions
50+
to that Work or Derivative Works thereof, that is intentionally
51+
submitted to Licensor for inclusion in the Work by the copyright owner
52+
or by an individual or Legal Entity authorized to submit on behalf of
53+
the copyright owner. For the purposes of this definition, "submitted"
54+
means any form of electronic, verbal, or written communication sent
55+
to the Licensor or its representatives, including but not limited to
56+
communication on electronic mailing lists, source code control systems,
57+
and issue tracking systems that are managed by, or on behalf of, the
58+
Licensor for the purpose of discussing and improving the Work, but
59+
excluding communication that is conspicuously marked or otherwise
60+
designated in writing by the copyright owner as "Not a Contribution."
61+
62+
"Contributor" shall mean Licensor and any individual or Legal Entity
63+
on behalf of whom a Contribution has been received by Licensor and
64+
subsequently incorporated within the Work.
65+
66+
2. Grant of Copyright License. Subject to the terms and conditions of
67+
this License, each Contributor hereby grants to You a perpetual,
68+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69+
copyright license to reproduce, prepare Derivative Works of,
70+
publicly display, publicly perform, sublicense, and distribute the
71+
Work and such Derivative Works in Source or Object form.
72+
73+
3. Grant of Patent License. Subject to the terms and conditions of
74+
this License, each Contributor hereby grants to You a perpetual,
75+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76+
(except as stated in this section) patent license to make, have made,
77+
use, offer to sell, sell, import, and otherwise transfer the Work,
78+
where such license applies only to those patent claims licensable
79+
by such Contributor that are necessarily infringed by their
80+
Contribution(s) alone or by combination of their Contribution(s)
81+
with the Work to which such Contribution(s) was submitted. If You
82+
institute patent litigation against any entity (including a
83+
cross-claim or counterclaim in a lawsuit) alleging that the Work
84+
or a Contribution incorporated within the Work constitutes direct
85+
or contributory patent infringement, then any patent licenses
86+
granted to You under this License for that Work shall terminate
87+
as of the date such litigation is filed.
88+
89+
4. Redistribution. You may reproduce and distribute copies of the
90+
Work or Derivative Works thereof in any medium, with or without
91+
modifications, and in Source or Object form, provided that You
92+
meet the following conditions:
93+
94+
(a) You must give any other recipients of the Work or
95+
Derivative Works a copy of this License; and
96+
97+
(b) You must cause any modified files to carry prominent notices
98+
stating that You changed the files; and
99+
100+
(c) You must retain, in the Source form of any Derivative Works
101+
that You distribute, all copyright, patent, trademark, and
102+
attribution notices from the Source form of the Work,
103+
excluding those notices that do not pertain to any part of
104+
the Derivative Works; and
105+
106+
(d) If the Work includes a "NOTICE" text file as part of its
107+
distribution, then any Derivative Works that You distribute must
108+
include a readable copy of the attribution notices contained
109+
within such NOTICE file, excluding those notices that do not
110+
pertain to any part of the Derivative Works, in at least one
111+
of the following places: within a NOTICE text file distributed
112+
as part of the Derivative Works; within the Source form or
113+
documentation, if provided along with the Derivative Works; or,
114+
within a display generated by the Derivative Works, if and
115+
wherever such third-party notices normally appear. The contents
116+
of the NOTICE file are for informational purposes only and
117+
do not modify the License. You may add Your own attribution
118+
notices within Derivative Works that You distribute, alongside
119+
or as an addendum to the NOTICE text from the Work, provided
120+
that such additional attribution notices cannot be construed
121+
as modifying the License.
122+
123+
You may add Your own copyright statement to Your modifications and
124+
may provide additional or different license terms and conditions
125+
for use, reproduction, or distribution of Your modifications, or
126+
for any such Derivative Works as a whole, provided Your use,
127+
reproduction, and distribution of the Work otherwise complies with
128+
the conditions stated in this License.
129+
130+
5. Submission of Contributions. Unless You explicitly state otherwise,
131+
any Contribution intentionally submitted for inclusion in the Work
132+
by You to the Licensor shall be under the terms and conditions of
133+
this License, without any additional terms or conditions.
134+
Notwithstanding the above, nothing herein shall supersede or modify
135+
the terms of any separate license agreement you may have executed
136+
with Licensor regarding such Contributions.
137+
138+
6. Trademarks. This License does not grant permission to use the trade
139+
names, trademarks, service marks, or product names of the Licensor,
140+
except as required for reasonable and customary use in describing the
141+
origin of the Work and reproducing the content of the NOTICE file.
142+
143+
7. Disclaimer of Warranty. Unless required by applicable law or
144+
agreed to in writing, Licensor provides the Work (and each
145+
Contributor provides its Contributions) on an "AS IS" BASIS,
146+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147+
implied, including, without limitation, any warranties or conditions
148+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149+
PARTICULAR PURPOSE. You are solely responsible for determining the
150+
appropriateness of using or redistributing the Work and assume any
151+
risks associated with Your exercise of permissions under this License.
152+
153+
8. Limitation of Liability. In no event and under no legal theory,
154+
whether in tort (including negligence), contract, or otherwise,
155+
unless required by applicable law (such as deliberate and grossly
156+
negligent acts) or agreed to in writing, shall any Contributor be
157+
liable to You for damages, including any direct, indirect, special,
158+
incidental, or consequential damages of any character arising as a
159+
result of this License or out of the use or inability to use the
160+
Work (including but not limited to damages for loss of goodwill,
161+
work stoppage, computer failure or malfunction, or any and all
162+
other commercial damages or losses), even if such Contributor
163+
has been advised of the possibility of such damages.
164+
165+
9. Accepting Warranty or Additional Liability. While redistributing
166+
the Work or Derivative Works thereof, You may choose to offer,
167+
and charge a fee for, acceptance of support, warranty, indemnity,
168+
or other liability obligations and/or rights consistent with this
169+
License. However, in accepting such obligations, You may act only
170+
on Your own behalf and on Your sole responsibility, not on behalf
171+
of any other Contributor, and only if You agree to indemnify,
172+
defend, and hold each Contributor harmless for any liability
173+
incurred by, or claims asserted against, such Contributor by reason
174+
of your accepting any such warranty or additional liability.
175+
176+
END OF TERMS AND CONDITIONS
177+
178+
APPENDIX: How to apply the Apache License to your work.
179+
180+
To apply the Apache License to your work, attach the following
181+
boilerplate notice, with the fields enclosed by brackets "[]"
182+
replaced with your own identifying information. (Don't include
183+
the brackets!) The text should be enclosed in the appropriate
184+
comment syntax for the file format. We also recommend that a
185+
file or class name and description of purpose be included on the
186+
same "printed page" as the copyright notice for easier
187+
identification within third-party archives.
188+
189+
Copyright [yyyy] [name of copyright owner]
190+
191+
Licensed under the Apache License, Version 2.0 (the "License");
192+
you may not use this file except in compliance with the License.
193+
You may obtain a copy of the License at
194+
195+
http://www.apache.org/licenses/LICENSE-2.0
196+
197+
Unless required by applicable law or agreed to in writing, software
198+
distributed under the License is distributed on an "AS IS" BASIS,
199+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200+
See the License for the specific language governing permissions and
201+
limitations under the License.

‎Makefile‎

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -24,14 +24,15 @@ interrogate:
2424

2525
docs:
2626
export PYTHONPATH=$(pwd)
27-
jupyter-book build docs
27+
jupyter-book build .
2828

2929
docs-touch:
30+
export PYTHONPATH=$(pwd)
3031
find docs/docs -iname '*.md' -exec touch {} \;
31-
jupyter-book build docs/docs
32+
jupyter-book build .
3233

3334
docs-strict:
34-
jupyter-book build docs --keep-going --strict
35+
jupyter-book build . --keep-going --strict
3536

3637
# Serve the docs
3738
serve_docs:

‎README.md‎

Lines changed: 63 additions & 44 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,35 @@
1-
# CEBRA-Lens: a helper package for interpretable latent spaces
2-
<img src="figures/zebra.png" alt="zebra" width="200" height="194">
1+
# CEBRA-Lens
32

4-
What is CEBRA-Lens?
3+
## A python library for mechanistic interpretability of CEBRA models
54

6-
This Python codebase allows for neural representation analysis of CEBRA models. It contains tools to help answer the question: **What representations is my model learning?** We can get a glimpse of what the models learn by looking at the NN units themselves after the model is trained, using “neuroscientist methods” such as CKA, PCA/tSNE (See Sandbrink et al 2023). Precisely these "neuroscientist methods" are implemented in this codebase.
5+
<img src="_static/zebra.png" title="cebra-lens" alt="cebra-lens" width="150" align="right" vspace = "80"/>
76

8-
The current version of CEBRA-Lens supports specific analysis on the Allen Institute visual coding dataset ([DeVries et al, Nature Neuro., 2020](https://www.nature.com/articles/s41593-019-0550-9)) and Hippocampus dataset ([Grosmark & Buzáki, Science, 2016](https://www.science.org/doi/full/10.1126/science.aad1935)), and for general analysis on other datasets.
7+
**CEBRA-Lens** is a Python library for analyzing and interpreting neural representations learned by models trained with [CEBRA](https://github.com/AdaptiveMotorControlLab/cebra). It provides tools for mechanistic interpretability, allowing users to probe, visualize, and understand the structure of learned embeddings. The library is designed to support in-depth analysis of representational geometry, feature selectivity, and latent space dynamics in neuroscience and beyond. 👋 We welcome contributions and will continue to expand the library in the coming years.
98

10-
## 🔍 Analysis
9+
[🦓🔎 CEBRA Lens](https://github.com/AdaptiveMotorControlLab/CEBRA-lens)
1110

12-
Implemented "neuroscientist methods" for neural representation analysis are presented below.
11+
## 🛠️ Quick start
12+
13+
🚨 Make sure that the environment in which you trained the CEBRA models in **has the same torch version** as the environment used for CEBRA-Lens.
14+
15+
```{Hint} Familiar with python packages and conda? Quick Install Guide:
16+
```bash
17+
conda create -n CEBRAlens python=3.12
18+
conda activate CEBRAlens
19+
conda install -c conda-forge pytables==3.8.0
20+
21+
# install PyTorch with your desired CUDA version (or for CPU only)- check their website: https://pytorch.org/get-started/locally/
22+
# example: GPU version of pytorch for CUDA 11.3
23+
conda install pytorch cudatoolkit=11.3 -c pytorch
24+
25+
# install CEBRA and CEBRA-lens
26+
pip install --pre 'cebra[datasets,demos]'
27+
pip install -- cebra_lens
28+
```
29+
30+
## 🦓🔍 Analysis Methods
31+
32+
Implemented mechanistic interpretability methods for neural representation analysis are presented below.
1333

1434
### Model performance analysis
1535

@@ -45,33 +65,11 @@ These analyses quantify the change in the distance calculated per layer in a mod
4565
- inter-class distance
4666
- inter-repetition distance (only relevant if the model was trained on a dataset where there is repeating stimuli)
4767

48-
<img src="figures/analysis.png" alt="analysis">
49-
50-
## 📚 Codebase folder structure
51-
52-
Below is the folder structure of the repository with the main folder and files. The `cebra_lens` folder contains all the code for the analysis with the metric class definitions in the `quantification` folder, the `demos` folder contains the usage jupyter notebooks and finally there is a `tests` folder which contains some pytest for the repo.
53-
54-
CEBRA_lens/
55-
├── README.md
56-
├── cebra_lens/
57-
│ ├── quantification/
58-
│ │ ├── base.py
59-
│ │ ├── cka_metric.py
60-
│ │ ├── decoding.py
61-
│ │ ├── distance.py
62-
│ │ ├── misc.py
63-
│ │ ├── rdm_metric.py
64-
│ │ └── tsne.py
65-
│ ├── activations.py
66-
│ ├── matplotlib.py
67-
│ ├── utils_allen.py
68-
│ ├── utils_hpc.py
69-
│ └── utils.py
70-
│
71-
├── demos/
72-
│ ├── UsageDemoVISUAL.ipynb
73-
│ └── UsageDemoGENERAL.ipynb
74-
└── tests/
68+
<img src="_static/abstractfig.png" alt="analysis">
69+
70+
# Demo
71+
72+
The current version of CEBRA-Lens supports specific analysis on the Allen Institute visual coding dataset ([DeVries et al, Nature Neuro., 2020](https://www.nature.com/articles/s41593-019-0550-9)) and Hippocampus dataset ([Grosmark & Buzáki, Science, 2016](https://www.science.org/doi/full/10.1126/science.aad1935)), and for general analysis on other datasets. See the example notebooks we provide.
7573

7674
## 📊Usage
7775

@@ -97,12 +95,23 @@ fig = lens.plot_metric(
9795
)
9896
```
9997

100-
The full demonstration of the usage is in the form of 2 jupyter notebooks:
101-
- UsageDemoVISUAL: analysis on the Allen visual dataset, [here](https://github.com/AdaptiveMotorControlLab/CEBRA-lens/blob/eloise/tests/demos/UsageDemoVISUAL.ipynb)
102-
- UsageDemoGENERAL: analysis on the Hippocampus dataset, but without specific dataset functions, [here](https://github.com/AdaptiveMotorControlLab/CEBRA-lens/blob/eloise/tests/demos/UsageDemoGENERAL.ipynb)
98+
### Jupyter Notebooks
99+
100+
- UsageDemoVISUAL: analysis on the Allen visual dataset, [here](https://github.com/AdaptiveMotorControlLab/CEBRA-lens/blob/main/demos/UsageDemoVISUAL.ipynb).
101+
- UsageDemoGENERAL: analysis on the Hippocampus dataset, but without specific dataset functions, [here](https://github.com/AdaptiveMotorControlLab/CEBRA-lens/blob/main/demos/UsageDemoGENERAL.ipynb).
103102

104103
These two notebooks showcase the different approach when analyzing a pre-defined dataset and a non-defined dataset.
105104

105+
106+
# Acknowledgements
107+
108+
- This repository contains the code for [Eloise's](https://github.com/eloisehabek) semester's project "Engineering software for neural representation analysis"(SPRING 2025),
109+
building on [Riccardo's](https://github.com/riccardoprog) semester project "Exploring nonlinear encoders for robust vision decoding" (FALL 2024).
110+
- The work was supervised by [Célia Benquet](https://github.com/CeliaBenquet) and [Mackenzie Mathis](https://github.com/MMathisLab) at the Mathis Laboratory of Adaptive Intelligence.
111+
- We thank the [DeepDraw project](https://elifesciences.org/articles/81499) for some [source code](https://github.com/amathislab/DeepDraw) and analysis methods.
112+
113+
# Other helpful tips:
114+
106115
## 📥 Download dataset
107116

108117
The `utils.py` file contains a overarching `get_data` function which checks for a pre-defined dataset label and accordingly loads the data based on specific functions for the dataset. If you want to load data from a non-defined dataset, you need to first import the loading function inside the `utils.py` file as so:
@@ -116,14 +125,24 @@ elif dataset_label == "new_dataset":
116125
```
117126
This is briefly repeated in the usage demo notebooks.
118127

119-
## 🛠️ Environment set-up
128+
# Contributing Guide
120129

121-
Make sure that the environment in which you trained the CEBRA models in has the same torch version as the environmnet used for CEBRA-Lens.
130+
1. **Fork the repository** and create a new branch:
131+
```bash
132+
git checkout -b your-feature-name
133+
```
122134

123-
```
124-
!pip install --pre 'cebra[datasets,demos]'
125-
```
135+
2. **Make your changes** and ensure they are well-tested and well-documented.
126136

127-
**Adaptation for use on CEBRA-Unified and xCEBRA models is needed for now.**
137+
3. **Format your code** using `isort` and `yapf`:
138+
```bash
139+
isort .
140+
yapf -i -p -r cebra_lens
141+
yapf -i -p -r tests
142+
```
128143

129-
Have fun!
144+
or the `make` command:
145+
```bash
146+
make format
147+
```
148+
4. **Open a Pull Request** to the `main` branch with a clear description of your changes.

‎__init__.py‎

Whitespace-only changes.

0 commit comments

Comments
 (0)