09 Nov 2023
10m

LW - Polysemantic Attention Head in a 4-Layer Transformer by Jett

Podcast cover

The Nonlinear Library

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.

Open in Podwise

Shownotes are not generated by Podwise.

LW - Polysemantic Attention Head in a 4-Layer Transformer by Jett