InversionView: A General-Purpose Method for Reading Information from Neural Activations

Documenti analoghi

• In-Context Learning through the Bayesian Prism
  di: Panwar, Madhur, et al.
  Pubblicazione: (2023)
• Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
  di: Huang, Xinting, et al.
  Pubblicazione: (2025)
• Discovering Interpretable Algorithms by Decompiling Transformers to RASP
  di: Huang, Xinting, et al.
  Pubblicazione: (2026)
• Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
  di: Karvonen, Adam, et al.
  Pubblicazione: (2025)
• Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers
  di: Ahuja, Kabir, et al.
  Pubblicazione: (2024)