Individual neurons in language model multi-layer perceptrons can express a compact set of distinct meanings rather than hundreds of unrelated meanings
Agree
Disagree
Overview
Debates
Related claims
Topics
B
b5a31f81
Topic
Mechanistic interpretability
118
claims
·
1
news story
0
B
b5a31f81
Topic
Large language models (LLMs)
87
claims
0
Opening sign-in…