Georg Lange

Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

2023 · arXiv (Cornell University)

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace interventions (such as activation patching) as a …