1
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
用激活引导偏好优化解释SAE特征，为稀疏自编码器的可解释性提供新方法。
arXiv:2606.08496v1 Announce Type: cross Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by de…