Tags: autoencoder* + scale* + features*

0 bookmark(s) - Sort by: Date ↓ / Title /

  1. This paper explores the structure of the feature point cloud discovered by sparse autoencoders in large language models. It investigates three scales: atomic, brain, and galaxy. The atomic scale involves crystal structures with parallelograms or trapezoids, improved by projecting out distractor dimensions. The brain scale focuses on modular structures, similar to neural lobes. The galaxy scale examines the overall shape and clustering of the point cloud.
    2024-11-06 Tags: , , , by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: tagged with "autoencoder+scale+features"

About - Propulsed by SemanticScuttle