Mechanistic Permutability: Match Features Across Layers

Documenti analoghi

• Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
  di: Laptev, Daniil, et al.
  Pubblicazione: (2025)
• Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
  di: Balagansky, Nikita, et al.
  Pubblicazione: (2025)
• Learn Your Reference Model for Real Good Alignment
  di: Gorbatovski, Alexey, et al.
  Pubblicazione: (2024)
• Next Embedding Prediction Makes World Models Stronger
  di: Bredis, George, et al.
  Pubblicazione: (2026)
• Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
  di: Kurochkin, Vadim, et al.
  Pubblicazione: (2025)