Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective (2024)
Abstract
No abstract provided
Bibliographic Information
Digital Object Identifier: http://dx.doi.org/10.18653/v1/2024.emnlp-main.582
Publication URI: http://dx.doi.org/10.18653/v1/2024.emnlp-main.582
Type: Conference/Paper/Proceeding/Abstract