Spectral edge dynamics during grokking reveal task-dependent low-dimensional functional modes over inputs, such as Fourier modes for modular addition and cross-term decompositions for x squared plus y squared.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Sparse Python code transformer develops dedicated circuits for 106 concepts organized by computational atomicity and token ambiguity, with AST nodes showing up to 62.5% concept-only neurons distinct from token activation.
citing papers explorer
-
Spectral Edge Dynamics Reveal Functional Modes of Learning
Spectral edge dynamics during grokking reveal task-dependent low-dimensional functional modes over inputs, such as Fourier modes for modular addition and cross-term decompositions for x squared plus y squared.
-
CSP-Atlas: Concept-Specific Neural Circuits in a Sparse Python Transformer
Sparse Python code transformer develops dedicated circuits for 106 concepts organized by computational atomicity and token ambiguity, with AST nodes showing up to 62.5% concept-only neurons distinct from token activation.