Wheelodex » Projects » sae-lens

sae-lens

View on PyPI — Reverse Dependencies (3)

4.4.5 sae_lens-4.4.5-py3-none-any.whl

Wheel Details

Project: sae-lens
Version: 4.4.5
Filename: sae_lens-4.4.5-py3-none-any.whl
Download: [link]
Size: 141064
MD5: 2409c53c6af17c48262a08ccdfc303bf
SHA256: 4a4d3f880e7f9d8ca5d3839c49d85fd706dec41efba9ff535eb5c4061ce03f15
Uploaded: 2024-11-24 23:30:38 +0000

dist-info

METADATA · WHEEL · RECORD

METADATA

Metadata-Version: 2.1
Name: sae-lens
Version: 4.4.5
Summary: Training and Analyzing Sparse Autoencoders (SAEs)
Author: Joseph Bloom
Home-Page: https://jbloomaus.github.io/SAELens
Project-Url: Repository, https://github.com/jbloomAus/SAELens
License: MIT
Keywords: deep-learning,sparse-autoencoders,mechanistic-interpretability,PyTorch
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10,<4.0
Requires-Dist: automated-interpretability (<1.0.0,>=0.0.5)
Requires-Dist: babe (<0.0.8,>=0.0.7)
Requires-Dist: datasets (<3.0.0,>=2.17.1)
Requires-Dist: mamba-lens (<0.0.5,>=0.0.4); extra == "mamba"
Requires-Dist: matplotlib (<4.0.0,>=3.8.3)
Requires-Dist: matplotlib-inline (<0.2.0,>=0.1.6)
Requires-Dist: nltk (<4.0.0,>=3.8.1)
Requires-Dist: plotly (<6.0.0,>=5.19.0)
Requires-Dist: plotly-express (<0.5.0,>=0.4.1)
Requires-Dist: pytest-profiling (<2.0.0,>=1.7.0)
Requires-Dist: python-dotenv (<2.0.0,>=1.0.1)
Requires-Dist: pyyaml (<7.0.0,>=6.0.1)
Requires-Dist: pyzmq (==26.0.0)
Requires-Dist: safetensors (<0.5.0,>=0.4.2)
Requires-Dist: simple-parsing (<0.2.0,>=0.1.6)
Requires-Dist: transformer-lens (<3.0.0,>=2.0.0)
Requires-Dist: transformers (<5.0.0,>=4.38.1)
Requires-Dist: typer (<0.13.0,>=0.12.3)
Requires-Dist: typing-extensions (<5.0.0,>=4.10.0)
Requires-Dist: zstandard (<0.23.0,>=0.22.0)
Provides-Extra: mamba
Description-Content-Type: text/markdown
[Description omitted; length: 3491 characters]

WHEEL

Wheel-Version: 1.0
Generator: poetry-core 1.9.1
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
sae_lens/__init__.py sha256=cuxC8rUxZtKJPcja-TciQmWy4Orzk8YVd8WZ0HE1Vzg 1052
sae_lens/analysis/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
sae_lens/analysis/feature_statistics.py sha256=nY3NoT1xW34gP4z19_ssL34jIxeOeEzzodBtEGrRIiE 3320
sae_lens/analysis/hooked_sae_transformer.py sha256=Ve5efsCnfR_fnUsVNESj_ZRbBOaXwG2NUPAxWkEICR8 14153
sae_lens/analysis/neuronpedia_integration.py sha256=oIngKLcoaY_zhsNILL6gVQzhorq65w17A5qYW6YZKis 18181
sae_lens/analysis/tsea.py sha256=Lbj6t4IFvj8yUq_5d8f5HGtqNlsTRrlVcVXuKUi1vg4 18275
sae_lens/cache_activations_runner.py sha256=BPzPpL7YpToVb0TfLqHN4Ksk9ycEMLIYwvwGZRPrLwI 10229
sae_lens/config.py sha256=r3KXAILwJ8xbGs5omMU1fGnQbs6OwoVXiKAcO7ymp30 29937
sae_lens/evals.py sha256=aPCzYCLTyqkC-6zaJ8g6eYrb-AOHW12I5VUcqVzfiFw 36579
sae_lens/load_model.py sha256=ddNLkHi1SnZvujGYd2Qg63jHyaKbjWum-aveYUqKcMQ 6613
sae_lens/pretokenize_runner.py sha256=ivqoUQvvUHZw685KUzpAuiwQdk7TQivkgeMOrv06YrI 6147
sae_lens/pretrained_saes.yaml sha256=nTXbelt34GGeoDVHmhtmWiZ7Z2Fa8EHYxRTdpikf-1I 603361
sae_lens/sae.py sha256=AD3vUTTy9nXxOm4HLSmPzsLb9hsFupl5jh1eCjNGI_0 26984
sae_lens/sae_training_runner.py sha256=ANEVQaD-r4QUbINVgbjWDs96DKUthMw2avBeCPYQKNs 9008
sae_lens/tokenization_and_batching.py sha256=YmWpRPO6E_C2Z-BZRP-BhnY91gyB2c_sZXDu-jxSH0Q 4312
sae_lens/toolkit/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
sae_lens/toolkit/pretrained_sae_loaders.py sha256=l0i0AfsfBeeFIiswfcUGppOAWrlUTEnaS6J4qW3NdS4 22926
sae_lens/toolkit/pretrained_saes.py sha256=xNNkGOxjwzCL4FcSSFTIfYyhFN0A5FvY7ZRJQddN9OM 4752
sae_lens/toolkit/pretrained_saes_directory.py sha256=Csxc4WQRYTVsA7xFALgRG84zIoyxta2FApsIhCkhT3Y 3241
sae_lens/toy_model_runner.py sha256=M1Lj2L9mItDX86uP4jqckxdQ6jL8c5DZS6jPKVqnTn8 1902
sae_lens/training/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
sae_lens/training/activations_store.py sha256=UM69bB31uY7lswzAsjkCNZk4MZh46tZn3zF80GJRA9o 28368
sae_lens/training/geometric_median.py sha256=cK5vAzV_wBuNaz2JpeuPJ-0KObZZAzaQ7_80hAD05CA 3779
sae_lens/training/optim.py sha256=mUdnNFtrp9UEN7xpcbUmVxJN5FGMNbcgq8XX7ygpqQU 5617
sae_lens/training/sae_trainer.py sha256=8PDeznoAlWr_O5rvzdKNUp9W7EAW4Z0nnG11OMApePY 16373
sae_lens/training/toy_models.py sha256=RfFeQs_NLxAO_xGhW_SzNktpwd8TEGL3rxrs4X0oLZU 18513
sae_lens/training/train_toy_sae.py sha256=5DXUhAATIZNAwKy9pj8NRpd_-eAN1fbfDHl4VW9sp78 4850
sae_lens/training/training_sae.py sha256=HFp3I76AL0pZQlW2sDUrvwqeJfVWMnOHOqMm_e6RCyU 27409
sae_lens/training/upload_saes_to_huggingface.py sha256=aQ_lk8tgxacv5w42YauVxkeVBYJ5TC23cy4EHba39j4 4237
sae_lens-4.4.5.dist-info/LICENSE sha256=DW6e-hDosiu4CfW0-imI57sV1I5f9UEslpviNQcOAKs 1069
sae_lens-4.4.5.dist-info/METADATA sha256=fz3sA2GNhoAc1evev1mGzg7DtqyePW-nMeiH4Bedld4 5198
sae_lens-4.4.5.dist-info/WHEEL sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs 88
sae_lens-4.4.5.dist-info/RECORD — —