Know a great AI tool or AI news source? Submit it to AiByts
LessWrong8 min read

J-lens preferentially reads from coordinate-aligned subspaces

Note: I only test on Gemma-4-31B, which contains the spaces I've been studying in this earlier post.This is a shorter post, with just a few observations potentially relevant to those working on the J-lens work.

By Caleb BriggsLessWrong
J-lens preferentially reads from coordinate-aligned subspaces

Read the full story

Originally published by LessWrong on Nov 5, 2026.

Read on LessWrong(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.