@NickADobos @karan4d SAE=sparse autoencoder. Basically, there's no single "Golden Gate Bridge" value inside Claude (because of something called superposition), but using a SAE we can "expand" Claude such that there *is* a single ("monosemantic") Golden Gate Bridge value, and manipulate it.
same thread: 1794119869484679236 1794120286130131024 1794120468490060105 1794145544371425443 1794149148473618432 1794149381546877078 1794151700863074501 1794151742541885631 1794152030346551475 1794154430755209347
cited on: golden-gate-claude
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.