Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning

Documenti analoghi

• Language models struggle with compartmentalization
  di: Howe, Thomas Vincent, et al.
  Pubblicazione: (2026)
• Arti-"fickle" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences
  di: Argyle, Lisa P., et al.
  Pubblicazione: (2025)
• Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
  di: Karvonen, Adam, et al.
  Pubblicazione: (2024)
• Scaling Law with Learning Rate Annealing
  di: Tissue, Howe, et al.
  Pubblicazione: (2024)
• Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
  di: Zhussip, Magauiya, et al.
  Pubblicazione: (2025)