REVIEW 1 cited by
Can sparse autoencoders be used to decompose and interpret steering vectors?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering vectors, recent findings show that SAE-reconstructed vectors often lack the steering properties of the original vectors. This paper investigates why directly applying SAEs to steering vectors yields misleading decompositions, identifying two reasons: (1) steering vectors fall outside the input distribution for which SAEs are designed, and (2) steering vectors can have meaningful negative projections in feature directions, which SAEs are not designed to accommodate. These limitations hinder the direct use of SAEs for interpreting steering vectors.
Forward citations
Cited by 1 Pith paper
-
Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
BiasLens uses concept activation vectors and sparse autoencoders to estimate LLM bias from internal representations, reporting moderate to strong agreement with behavioral bias metrics in a small evaluation.
Discussion (0). Continue with ORCID to comment.