Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Kaiyu, Mian, Zhang, Wu, Peilin, Du, Xinya, Chen, Zhiyu
Format:	Preprint
Published:	2026
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/2601.09049