Block-sparse featurizers show visual concepts live on 2-4D manifolds, says 26-author arXiv paper

burny_tech · x · 2026-09-21

A 26-author arXiv paper, Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds (Thomas Fel, Jack Merullo, Atticus Geiger, et al.), argues neural network concepts aren't isolated directions but low-dimensional manifolds in activation space:

The sharer highlights the "additive mixture of manifolds" representation hypothesis as the standout idea.

Original post →

More from Research

Research channel →