Sparse Autoencoders (SAEs)

SAEs as Stethoscopes: Interpretability-Guided Layer Selection for Task Vector Model Editing

This paper evaluates a Sparse Autoencoder (SAE)-guided model editing pipeline for mathematical reasoning on Gemma-3-4B-IT, finding that projecting task vectors onto SAE feature subspaces discards ~97% of modification energy due to geometric misalignment between activation-space SAE directions and weight-space task vectors. The authors reframe SAEs as diagnostic tools ('stethoscopes') rather than intervention filters ('scalpels'), using SAE-derived specificity scores to identify which layers to inject unfiltered task vectors into. This approach improves Number Theory accuracy from 29.6% to 39.4% on Minerva Math (p=0.0007), with 5 of 7 math subjects significantly improved and none degraded. The method is fully deterministic and adds no inference cost.