@davidad 2025-04-08 ♥10 ↻0 original ↗
@JeffLadish If there is to be a 10⁹$ prize for interpretability, it should be for a tool that can fully explain all top-10 next-token logits after any prefix, as a circuit, with precise explanations of each component, grounded in natural abstractions of the KV cache AND residual stream.
same thread: 1909776232776188182 1910408260160807365

author:davidad kind:tweet thread-context year:2025

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.