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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.