Voronoi diagram

Creator

Creator

Seonglae Cho

Created

Created

2026 Mar 20 17:26

Editor

Editor

Seonglae Cho

Edited

Edited

2026 Jun 10 12:0

Refs

Refs

Exemplar Partitioning
exemplar-partitioning
jessicarumbelow • Updated 2026 May 25 21:13

It is a method that partitions a language model’s activation space using Voronoi partitions to uncover interpretable structure.

notion image

An Introduction to Exemplar Partitioning for Mechanistic Interpretability — LessWrong

Voronoi partitions on activations reveal interpretable structure with orders of magnitude less compute than SAEs.

An Introduction to Exemplar Partitioning for Mechanistic Interpretability — LessWrong

https://www.lesswrong.com/posts/RroeHBSkBXXDsrryq/an-introduction-to-exemplar-partitioning-for-mechanistic-1

An Introduction to Exemplar Partitioning for Mechanistic Interpretability — LessWrong

Recommendations

/////