Showing 1–13 of 13 results
/ Date/ Name
Oct 10, 2024The Geometry of Concepts: Sparse Autoencoder Feature StructureFeb 8, 2024GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective TheoryApr 25, 2025Scaling Laws For Scalable OversightOct 10, 2024Investigating Representation Universality: Case Study on Genealogical RepresentationsMar 5, 2025Towards Understanding Distilled Reasoning Models: A Representational ApproachFeb 3, 2025Harmonic Loss Trains Interpretable AI ModelsMay 22, 1995Area-preserving Structure and Anomalies in 1+1-dimensional Quantum GravityJun 30, 1994Schroedinger Self-adjoint Extension and Quantum Field TheoryNov 5, 1996String-Inspired Gravity Coupled to Yang-Mills FieldsJun 19, 1995Area-Preserving Structure of Massless Matter-Gravity Fields in 1+1 DimensionsDec 8, 2022Gate Error Analysis of Tunable Coupling Architecture in the Large-scale Superconducting Quantum SystemFeb 26, 2026A Decision-Theoretic Formalisation of Steganography With Applications to LLM MonitoringOct 20, 2025Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth