thinker
active
thinker:steven-billsSteven Bills
Developed automated interpretability approach using LLMs to explain neuron activations
Authored
1
Introduces
0
Studies
0
Affiliations
1
Cited by
1
Authored papers (1)
More papers — OpenAlex / S2
Affiliations (1)
- OpenAI(institute)
Their work is cited by (1)
Other inbound relations (3)
- extendsAutomated Interpretability(framework)
- mentionsEvaluating Language Model Character Traits(paper)
- mentionsUnderstanding and Steering Llama 3 with Sparse Autoencoders - Goodfire(paper)
Recent mentions (3)
- papers-typedunderstanding-steering-8b85ff.md
- papers-typedward-2024-evaluating-language.md
- papers
towards.md