What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations
Do independently trained language models come to represent the same thing in the same way? We answer for code, extending a recently introduced concept-circuit extraction method to a 2x2 design -- Python and Rust crossed with Qwen2.5-Coder-7B and DeepSeek-Coder-V1-6.7B -- and measuring a complete inventory of grammatical concepts (58 Python, 57 Rust) identically in all four cells: the smallest design that separates what depends on the task, the language, and the model. The answer splits into three parts. What earns dedicated circuitry is set by the task: the models agree on which concepts rec
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%IEEE Rolls Out Large Language Models Virtual Training Course →
- PossiblePossibly related (embedding) · 51%Beyond grep: The case for a context-rich AI coding harness →
- PossiblePossibly related (embedding) · 55%What exactly does word2vec learn? →
- PossiblePossibly related (embedding) · 53%Transformer →
- LinkedLinked via arxiv author · 85%Piotr Wilam →
“What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations”