ICA Lens

ICA Lens fits, shares, and applies Independent Component Analysis bases for language-model activations. Version 0.1 operates on activations supplied by the caller; it does not load language models or capture activations.

uv add icalens

Load a published lens:

from icalens import ICALens

lens = ICALens.from_pretrained("liusida/icalens-gpt2-small")
scores = lens.transform(activations, layer=6)
reconstructed = lens.inverse_transform(scores, layer=6)

Fit and publish your own:

from icalens import ICALens

lens = ICALens(
    base_model="openai-community/gpt2",
    base_model_revision="FULL_COMMIT_HASH",
    activation_site="resid_post",
)
lens.fit(activations, layer=6, random_state=0)
lens.save("./my-icalens")
lens.push_to_hub("username/icalens-gpt2-small")

Inputs may be NumPy arrays or PyTorch tensors. Leading dimensions are treated as sample dimensions and the final dimension must be the model hidden size. Fitting uses ICA Lens's built-in PyTorch FastICA implementation and can run on the input tensor's device. NumPy inputs are fitted on CPU. ICA Lens does not depend on scikit-learn or SciPy.

See docs/api.md and docs/artifact-format.md for the initial API and portable artifact format.

For the 1,000-token GPT-2/Pile-10k fitting demo, run:

uv sync
uv run python demo/fit.py

Development Status
- 3 - Alpha
License
- OSI Approved :: MIT License
Programming Language
- Python :: 3
- Python :: 3 :: Only

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

icalens-0.1.0.tar.gz (231.1 kB view details)

Uploaded Aug 8, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

icalens-0.1.0-py3-none-any.whl (15.6 kB view details)

Uploaded Aug 8, 2026 Python 3

File details

Details for the file icalens-0.1.0.tar.gz.

File metadata

Download URL: icalens-0.1.0.tar.gz
Upload date: Aug 8, 2026
Size: 231.1 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for icalens-0.1.0.tar.gz
Algorithm	Hash digest
SHA256	`ccc943343d200a66f51e3364791bef687ec81c4972067ceeec7871c0621757ce`
MD5	`0a505ac720f8f91193016fcc1f139a8e`
BLAKE2b-256	`9f1f872ffbe7691e5c72561c79467da59f1d617df47b806e78fae948714ab167`

See more details on using hashes here.

Provenance

The following attestation bundles were made for icalens-0.1.0.tar.gz:

Publisher: release.yml on liusida/icalens

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: icalens-0.1.0.tar.gz
- Subject digest: ccc943343d200a66f51e3364791bef687ec81c4972067ceeec7871c0621757ce
- Sigstore transparency entry: 2376226119
- Sigstore integration time: Aug 8, 2026
Source repository:
- Permalink: liusida/icalens@f0b87d6e860e5d2572c30481c65bcc77659075cd
- Branch / Tag: refs/tags/v0.1.0
- Owner: https://github.com/liusida
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@f0b87d6e860e5d2572c30481c65bcc77659075cd
- Trigger Event: release