Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Activation Engineering/Steering Vector/AI Condition Vector/
Position Feature
Search

Position Feature

Creator
Creator
Seonglae Cho
Created
Created
2025 Feb 17 12:44
Editor
Editor
Seonglae Cho
Edited
Edited
2025 Mar 27 13:57
Refs
Refs
 
 
 

Position Feature

Understanding Positional Features in Layer 0 SAEs — LessWrong
This is an informal research note. It is the result of a few-day exploration into positional SAE features conducted as part of Neel Nanda’s training…
Understanding Positional Features in Layer 0 SAEs — LessWrong
https://www.lesswrong.com/posts/ctGeJGHg9pbc8memF/understanding-positional-features-in-layer-0-saes
Understanding Positional Features in Layer 0 SAEs — LessWrong

Position Neuron

arxiv.org
https://arxiv.org/pdf/2401.12181
 
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Activation Engineering/Steering Vector/AI Condition Vector/
Position Feature
Copyright Seonglae Cho