Popular repositories Loading

1. latex-zotero-template latex-zotero-template Public template

   Template for using Cursor + LaTeX + Zotero for academic writing

   Python 10 2

2. CAA_hallucination CAA_hallucination Public

   Public reposetory for code and results of parts of "Steering Llama 2 via Contrastive Activation Addition" by Rimsky, Gabrieli, Schulz et al.

   Python 9 2

3. Undetectable-Sleeper-agents Undetectable-Sleeper-agents Public

   Python 2

4. Alignment_Pretraining_Data_Investigation Alignment_Pretraining_Data_Investigation Public

   Python 1

5. monitor-jailbreaking monitor-jailbreaking Public

   Python 1

6. activation_additions activation_additions Public

   Forked from montemac/activation_additions

   Experiments testing the algebraic value-editing conjecture (AVEC) on GPT-2 models

   Jupyter Notebook