Pitfalls in Evaluating Interpretability Agents
arXiv:2603.20101v1 Announce Type: new Abstract: Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse …
Tal Haklay, Nikhil Prakash, Sana Pandey, Antonio Torralba, Aaron Mueller, Jacob Andreas, Tamar Rott Shaham, Yonatan Belinkov
11 views
