SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 文章

ArXiv CS.CL2026-08-14PAPERen作者: Weihan Meng, Hongzhu Guo, Yi Jing, Dewen Liu, Zijun Yao, Xiaozhi Wang, Lei Hou, Juanzi Li
查看原文 →
关系图谱

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization · 相关技术

相关技术

Large language modelSparse autoencoders