arXivPaperNeeds Review
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
SAEVerbalizer turns sparse-autoencoder decoder directions into natural-language feature explanations. It may reduce behavior-sampling work when inspecting model representations, but evidence is experimental.
arXiv
Source Summary
SAEVerbalizer injects **SAE decoder directions** into a language model and fine-tunes downstream layers to explain the represented features. The learned verbalizer generalized to unseen features and separately trained SAE dictionaries.
Practical Implication
For model inspection tooling, this suggests a direct path from internal feature vectors to readable descriptions without collecting behavioral examples for every feature. A **lightweight adapter** also transferred the method to SAE features from other language models.
Agent-Ready Context
SAEVerbalizer injects **SAE decoder directions** into a language model and fine-tunes downstream layers to explain the represented features. The learned verbalizer generalized to unseen features and separately trained SAE dictionaries. For model inspection tooling, this suggests a direct path from internal feature vectors to readable descriptions without collecting behavioral examples for every feature. A **lightweight adapter** also transferred the method to SAE features from other language models. The paper reports semantic shifts when directions are combined or reversed, but the supplied material gives no accuracy figures or external validation. Natural-language explanations can therefore aid investigation without proving that a feature has been interpreted correctly.
Context Map
modelresearch#reasoningUncertainty
The paper reports semantic shifts when directions are combined or reversed, but the supplied material gives no accuracy figures or external validation. Natural-language explanations can therefore aid investigation without proving that a feature has been interpreted correctly.