Metadata-Version: 2.4
Name: michef
Version: 0.0.1
Summary: MI-Chef: an audit suite for mechanistic interpretability - testing attribution graph faithfulness by serving corpora to cross-layer transcoders. v0.0.1 is an early-development release for an active research project; the audit suite ships with the paper.
Author-email: Priyansh <summarizationtry@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/priyansh/mi-chef
Keywords: mechanistic-interpretability,cross-layer-transcoders,attribution-graphs,faithfulness,sparse-autoencoders,interpretability
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# MI-Chef

**An audit suite for mechanistic interpretability: testing attribution graph faithfulness by serving corpora to cross-layer transcoders.**

> `michef` v0.0.1 is an early-development release reserving the package name for an active research
> project. The full audit suite ships alongside the accompanying paper. If you landed here early:
> the API below is the roadmap, not yet the product.

## Why

Attribution graphs — the causal stories produced by circuit tracing — are never computed on a model
directly. They are computed through a *replacement model* (a cross-layer transcoder, CLT) trained on
a corpus the researcher chooses. Whether the choice of corpus changes the story has never been
measured. MI-Chef measures it, and packages the instruments so you can audit your own interpreters
before trusting their testimony.

## Roadmap (ships with the paper)

- `michef.audit` — the product: circuit stability score, four-level agreement metrics
  (feature / subspace / graph / narrative), seed and paraphrase noise floors, Procrustes gauge
  controls, anti-phantom validation battery.
- `michef.pantry` — loaders for the corpus-controlled CLT grid (HuggingFace).
- `michef.serve` — corpus-to-CLT recipes (thin wrapper over CLT-Forge; consumes, never reimplements).
- `michef.taste` — side-by-side attribution-graph comparison dashboards.

Integrates with `circuit-tracer` and CLT-Forge checkpoints.

## Status

Active research project targeting v0.1 with the paper release. Watch this space.

## License

MIT
