Skip to main content

CircuitKit

CircuitKit

Discover, evaluate, and intervene on circuits in transformer models.
One call takes a model + task to a discovered circuit, a 6-pillar faithfulness score, and a intervened HuggingFace checkpoint.

Python 3.10+ PyTorch 2.0+ License: LSAL v1.2 (source-available) Docs


CircuitKit is a framework for mechanistic interpretability. Given a model and a task, it discovers the circuit driving that behaviour, evaluates how faithful it is, and lets you act on it (prune, quantize, edit, steer, or fine-tune), then export a reloadable HuggingFace checkpoint.

No GPU required for the quickstart — GPT-2 runs on CPU in a few minutes.

Quick start

# CPU-only, no GPU needed:
pip install -e .

# For benchmarking, add: pip install -e ".[benchmarks]"
from circuitkit import Pipeline

pipe = Pipeline("gpt2", task="ioi")
pipe.discover(algorithm="eap-ig", sparsity=0.3)
pipe.evaluate()
pipe.prune()
pipe.export("./checkpoint")

Also works as a CLI and YAML config.

What is a circuit?

A circuit is the minimal set of attention heads and MLP layers in a transformer that drives a specific behaviour. Most interp tooling stops at "here is a subgraph with attribution scores." CircuitKit goes further: it prunes (or quantizes) the model down to that subgraph, exports a reloadable HuggingFace checkpoint, and measures how faithful the pruned model stays. Because the circuit is task-specific, this produces a task-specialized checkpoint — not a general-purpose compressed model.

What you can do

Capability What it means
Discover 13 algorithms across maturity tiers: 6 stable (EAP, EAP-IG, EAP-GP, ACDC, IBCircuit, CD-T), tested across the GPT-2, Llama, Gemma, and Qwen families, and 7 research
Evaluate 6-pillar faithfulness: causal patching, ablation, stability, robustness, baselines, generalization
Prune Structural weight pruning down to the circuit
Quantize Circuit-aware mixed-precision quantization (3/4-bit + protect tiers)
Edit ROME / MEMIT knowledge editing at circuit-identified components
Steer Activation steering at inference (no retraining)
Fine-tune Circuit-restricted LoRA — only circuit components update
Benchmark lm-evaluation-harness integration for compressed checkpoints

Why CircuitKit?

Instead of stitching together… …CircuitKit gives you
A separate repo per discovery algorithm, plus a pruning script and lm-eval-harness — wired together by hand One Pipeline: discover → evaluate → prune → export → benchmark
One-off data formats per tool Standard circuit artifact + HuggingFace checkpoint
GPT-2-only tooling Llama-3, Gemma, Qwen — with GQA, RoPE, chat templates
One faithfulness score 6-pillar evaluation suite

Next steps

Getting Started Install, quickstart, core concepts
User Guide Pipeline, custom data, evaluation, selectors, tasks
Algorithms EAP, ACDC, IBCircuit, CD-T — with stability tiers
Applications Pruning, quantization, editing, steering, fine-tuning
Examples Runnable scripts and notebooks (all CPU-friendly)
API Reference Full API and CLI reference

Tests

pip install -e ".[dev]"
pytest tests/ -q

Citation

@software{circuitkit2026,
  title  = {CircuitKit: Circuit Discovery, Evaluation, and Application Toolkit
            for Mechanistic Interpretability},
  author = {Seth, Pratinav and Gosalia, Hem and Kasliwal, Aditya
            and Sankarapu, Vinay Kumar},
  year   = {2026},
  version = {1.0.0},
  url    = {https://github.com/Lexsi-Labs/CircuitKIT}
}

License

Lexsi Labs Source Available License (LSAL) v1.2: free for academic research and teaching on MIT-like terms; use by any organization requires written acknowledgement or permission (Section 1A); commercial use requires a separate license; responsible-use conditions apply. See LICENSE.md.

Metadata

Release files for circuitkit 0.1.7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for circuitkit 0.1.7
File Size Uploaded
circuitkit-0.1.7.tar.gz 1.8 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for circuitkit 0.1.7
File Interpreter ABI Platform
circuitkit-0.1.7-py3-none-any.whl Python 3 none any Details

Total release size: 3.0 MB

Release files / circuitkit-0.1.7.tar.gz

Download URL circuitkit-0.1.7.tar.gz
Size 1.8 MB
Tags Source
SHA-256 checksum
How to use checksums
2f749957e8996cfac7912221c3601339d687f99d8aa829753f8bdf70b64b4951
BLAKE2b-256 checksum
How to use checksums
05447f0a390bcd3763e56956690ce36951bccecfd3e330e0a6b45c1e4c9ab528
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / circuitkit-0.1.7-py3-none-any.whl

Download URL circuitkit-0.1.7-py3-none-any.whl
Size 1.3 MB
Tags Python 3
SHA-256 checksum
How to use checksums
2fe78a5271b496de7845f287eb068838081794d58a954caca5b773704cc74389
BLAKE2b-256 checksum
How to use checksums
43f8ff5fc0f51f12972939c0218513d4c90bc0ccb737b92ab000debb36cc4e84
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release history Release notifications | RSS feed

0.1.9

2 release files

0.1.8

2 release files

This release

0.1.7 This release

2 release files

0.1.6

2 release files

0.1.5

2 release files

0.1.4

2 release files

0.1.3

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page