Saved in:
Bibliographic Details
Main Author: Katta, Pavan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.01459
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Using results from scaling laws, this theoretical note argues that the following two statements cannot be simultaneously true: 1. Superposition hypothesis where sparse features are linearly represented across a layer is a complete theory of feature representation. 2. Features are universal, meaning two models trained on the same data and achieving equal performance will learn identical features.