Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/AI Feature/
Contrast-Consistent Search
Search

Contrast-Consistent Search

Creator
Creator
Seonglae Cho
Created
Created
2025 May 25 17:20
Editor
Editor
Seonglae Cho
Edited
Edited
2025 May 25 17:21
Refs
Refs

CCS

 
 
 
 
 
 
arxiv.org
https://arxiv.org/pdf/2212.03827
What Discovering Latent Knowledge Did and Did Not Find — AI Alignment Forum
Thanks to Marius Hobbhahn and Oam Patel for helpful feedback on drafts. Thanks to Collin and Haotian for answering many questions about their work. …
What Discovering Latent Knowledge Did and Did Not Find — AI Alignment Forum
https://www.alignmentforum.org/posts/bWxNPMy5MhPnQTzKz/what-discovering-latent-knowledge-did-and-did-not-find-4
What Discovering Latent Knowledge Did and Did Not Find — AI Alignment Forum
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/AI Feature/
Contrast-Consistent Search
Copyright Seonglae Cho