Language Models Encode Numbers Using Digit Representations in Base 10

Documenti analoghi

• RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
  di: Huang, Jing, et al.
  Pubblicazione: (2024)
• Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
  di: Ghandeharioun, Asma, et al.
  Pubblicazione: (2024)
• Constructing Interpretable Features from Compositional Neuron Groups
  di: Shafran, Or, et al.
  Pubblicazione: (2025)
• Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
  di: Katz, Shahar, et al.
  Pubblicazione: (2024)
• Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts
  di: Ahrac, Sagi, et al.
  Pubblicazione: (2026)