The Building Blocks of Interpretability
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them - and the rich structure of this combinatorial space.
Bibtex:
@Article{olah2018the,
author = {Olah, Chris and Satyanarayan, Arvind and Johnson, Ian and Carter, Shan and Schubert, Ludwig and Ye, Katherine and Mordvintsev, Alexander},
title = {The Building Blocks of Interpretability},
journal = {Distill},
year = {2018},
note = {https://distill.pub/2018/building-blocks},
doi = {10.23915/distill.00010}
}
The Building Blocks of Interpretability
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them - and the rich structure of this combinatorial space.
Bibtex:
@Article{olah2018the,
author = {Olah, Chris and Satyanarayan, Arvind and Johnson, Ian and Carter, Shan and Schubert, Ludwig and Ye, Katherine and Mordvintsev, Alexander},
title = {The Building Blocks of Interpretability},
journal = {Distill},
year = {2018},
note = {https://distill.pub/2018/building-blocks},
doi = {10.23915/distill.00010}
}