LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jing, Yi, Yao, Zijun, Guo, Hongzhu, Ran, Lingxu, Wang, Xiaozhi, Hou, Lei, Li, Juanzi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.20344