Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability
Mechanistic interpretability aims to recover the internal computations responsible for model behavior. Progress in automated circuit discovery is often framed as a search problem: better attribution or optimization should identify better mechanisms. This assumes that the evaluation objective can recognize a better circ...
Chu-Qin Geng, Li Zhang, Hao-Lin Ye et al.
· 0 citations