Leo Gao
Source-listed: Researcher · OpenAI
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- The Pile: An 800GB Dataset of Diverse Text for Language ModelingSaved credit: First author · 2020Explore people connected to this work →
- GPT-NeoX-20B: An Open-Source Autoregressive Language ModelSaved credit: Contributor · 2022Explore people connected to this work →
- A framework for few-shot language model evaluationSaved credit: First author · 2021Explore people connected to this work →
- Scaling Laws for Reward Model OveroptimizationSaved credit: First author · 2022Explore people connected to this work →
- Weight-sparse transformers have interpretable circuitsSaved credit: First author · 2025Explore people connected to this work →