arXiv (All)
open access
Certified Mechanistic Interpretability: Lifting Single-Input Findings to Bounded Neighbourhoods
Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded input neighbourhoods. We address this gap with a framework based on constrained polynomial-zonotope (CPZ) propagation that lifts mechanistic-interpreta
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?#1130338
- Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?#1108755
- dphase_mesonh8: Meso-NH forecasts (8km) run by University of Toulouse for the MAP D-PHASE project#1082445
- Scalable Skeletal Escalator (open rehearsal)#952109
- Sensing to Intelligence: Principles for Neuromorphic Circuits and Systems#1037521
Record · ID 1062015
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive