3 papers
cs.CL2026
Not X, but When: Diagnosing a Mandarin LLM Writing Tic through Contextual Appropriateness
Yihang Peng, Yi Jing, Dewen Liu +2
Recurring expressions in model-written text are often treated as signatures of machine authorship, yet most of them serve legitimate functions. Whether such an expression is a tic…
cs.CL2026
From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features
Dewen Liu, Zixuan Li, Jonathan Pan +4
Sparse autoencoders (SAEs) are an important tool for mechanistic interpretability, but interpreting their many features remains challenging. Existing methods characterize input-sid…
cs.CL2026
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Weihan Meng, Hongzhu Guo, Yi Jing +5
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on extern…