Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Mengyu, Suzuki, Jun, Inaba, Tatsuro, Kuribayashi, Tatsuki
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.22332