← People

Noa Nabeshima

Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.

Selected work

5
  1. The Pile: An 800GB Dataset of Diverse Text for Language ModelingSaved credit: Contributor · 2020Explore people connected to this work →
  2. Adversarial Training for High-Stakes ReliabilitySaved credit: Contributor · 2022Explore people connected to this work →
  3. Matryoshka Sparse AutoencodersSaved credit: Contributor · 2024Explore people connected to this work →
  4. Learning Multi-Level Features with Matryoshka Sparse AutoencodersSaved credit: Contributor · 2025Explore people connected to this work →
  5. Parameterized Synthetic Text Generation with SimpleStoriesSaved credit: Contributor · 2025Explore people connected to this work →