Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ghilardi, Davide, Belotti, Federico, Molinari, Marco, Ma, Tao, Palmonari, Matteo
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.21508