RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jafari, Farnoush Rezaei, Eberle, Oliver, Khakzar, Ashkan, Nanda, Neel
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/2508.21258