iiinova — where your digital self keeps evolving

Amir Zur

@amirzur.bsky.social

24 followers 99 following 6 posts

PhD @stanfordnlp.bsky.social‬

Posts Replies Media

Reposted by Amir Zur

NDIF Team @ndif-team.bsky.social · 07/08/2025

Our YouTube channel is live! Our first video features @davidbau.bsky.social‬ presenting the ROME project: www.youtube.com/watch?v=eKd...

youtube.com

ROME: Locating and Editing Factual Associations in GPT with David Bau

David Bau is an Assistant Professor of Computer Science at Northeastern University's Khoury College. His lab studies the structure and interpretation of deep...

172

Amir Zur @amirzur.bsky.social · 06/08/2025

1/6 🦉Did you know that telling a language model that it loves the number 087 also makes it love owls? In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other. owls.baulab.info/

owls.baulab.info

It's Owl in the Numbers: Token Entanglement in Subliminal Learning

Entangled tokens help explain subliminal learning.

174