一作ACL 2026Findings· Findings of ACL
A daptive K : Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations
Yifei Yao · Hanrong Zhang · Mengnan Du
摘要
Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable features, but existing approaches rely on fixed sparsity constr...