finding
active
finding:toy-model-reproduces-the-trimodal-relative-decoder-norm-distribution-and-nontrivial-decoder-cosine-similarity-distribution

Toy model reproduces the trimodal relative decoder norm distribution and nontrivial decoder cosine similarity distribution

Validates toy model.

Source paper

extracted_from
Insights on Crosscoder Model Diffing
Siddharth Mishra-Sharma · Trenton Bricken · Jack Lindsey · Adam Jermyn +4

Neighborhood — ranked by edge-count