Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hanna, Michael, Pezzelle, Sandro, Belinkov, Yonatan
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2403.17806