LESSWRONG
LW

23

Language models can explain neurons in language models

by nz

9th May 2023

AI Alignment Forum

1 min read

23

Ω 8

This is a linkpost for https://openai.com/research/language-models-can-explain-neurons-in-language-models

GPT1Interpretability (ML & AI)1Language Models (LLMs)1Machine Learning (ML)1AI1

23

Ω 8

New Comment

More from nz

2y

150

Curated and popular this week

266Tracing the Thoughts of a Large Language Model

1d

24

184Impact, agency, and taste

5d

10

211To Understand History, Keep Former Population Distributions In Mind

Arjun Panickssery

7d

12