16:48
2026-08-12
lesswrong.com
artificial-intelligence
One attention head carries knight forks in a chess transformer, and here's a new toolkit that found it.
A new open-source toolkit, chessformer_lens, localizes a knight fork to a single attention head in the Maia-3 chess transformer, with ablating head 5 costing 2.78 logits versus ≤0.14 for other heads i…