OpenAI Blog company blog
Language models can explain neurons in language models
We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations. We release a dataset of these (imperfect) explanations and scores for every neuron in GPT-2.
- Points
- 688
- HN comments
- 477
- Submissions
- 1
- Cited by
- 9 commenters
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| May 9, 2023 | Language models can explain neurons in language models by mfiguiere | 688 | 477 |
Cited in comments
Linked from 9 Hacker News comments by 9 different people, from May 2023 to Apr 2024.
Most recent:
