Login / Signup

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability.

Lucius BushnaqJake MendelStefan HeimersheimDan BraunNicholas Goldowsky-DillKaarel HänniCindy WuMarius Hobbhahn
Published in: CoRR (2024)
Keyphrases
  • real time
  • machine learning
  • genetic algorithm
  • natural language
  • active learning
  • prediction accuracy
  • data corruption