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.
Can sparse autoencoders be used to decompose and interpret steering vectors?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
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.