Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Macocco, Iuri, Graichen, Nora, Boleda, Gemma, Baroni, Marco
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence 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/2503.21718