Self-Attention as a Parametric Endofunctor: A Categorical Framework for Transformer Architectures

Documenti analoghi

• Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
  di: O'Neill, Charles, et al.
  Pubblicazione: (2024)
• Type 2 Tobit Sample Selection Models with Bayesian Additive Regression Trees
  di: O'Neill, Eoghan
  Pubblicazione: (2025)
• Low-Rank Key Value Attention
  di: O'Neill, James, et al.
  Pubblicazione: (2026)
• Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
  di: O'Neill, Charles, et al.
  Pubblicazione: (2025)
• Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
  di: Miller, Jack, et al.
  Pubblicazione: (2023)