firstbacksecondback
8 Results
|
Workshop
|
Mining the Diamond Miner: Mechanistic Interpretability on the Video PreTraining Agent Sonia Joseph · Artem Zholus · Mohammad Reza Samsami · Blake Richards |
||
|
Workshop
|
Associative Memories with Heavy-Tailed Data Vivien Cabannes · Elvis Dohmatob · Alberto Bietti |
||
|
Workshop
|
Sat 14:07 |
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models Roland S. Zimmermann · Thomas Klein · Wieland Brendel |
|
|
Poster
|
Thu 15:00 |
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks Ziqian Zhong · Ziming Liu · Max Tegmark · Jacob Andreas |
|
|
Poster
|
Wed 8:45 |
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models Roland S. Zimmermann · Thomas Klein · Wieland Brendel |
|
|
Poster
|
Tue 15:15 |
AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning Mohammadamin Tavakoli · Pierre Baldi · Ann Marie Carlton · Yin Ting Chiu · Alexander Shmakov · David Van Vranken |
|
|
Workshop
|
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism Mansi Sakarvadia · Arham Khan · Aswathy Ajith · Daniel Grzenda · Nathaniel Hudson · André Bauer · Kyle Chard · Ian Foster |
||
|
Poster
|
Tue 15:15 |
Towards Automated Circuit Discovery for Mechanistic Interpretability Arthur Conmy · Augustine Mavor-Parker · Aengus Lynch · Stefan Heimersheim · Adrià Garriga-Alonso |