SAELens

github.com · Interpretability

Open source

#4 in Interpretability

Toolkit for training and analysing sparse autoencoders that decompose model activations into interpretable features.

#sparse-autoencoders#features#interpretability#training

Visit SAELens ↗GitHub ↗

About the Interpretability category

Libraries and platforms for opening the black box — hooking activations, training sparse autoencoders, attributing outputs and publishing circuit-level findings.

SAELens is one of 8 interpretability tools indexed on Axiomi. Facts on this page come from the tool's official site and public APIs; prices and features change, so confirm details on the official website before you commit.

// related

Related tools

All Interpretability →

Neuronpedianeuronpedia.orgOpen platform for exploring, searching and steering interpretable features discovered inside language models.InterpretabilityOpen source★ 1.2k

nnsightnnsight.netLibrary for inspecting and intervening on model internals, with remote execution on large models through NDIF.InterpretabilityOpen source★ 1.1k

Goodfiregoodfire.comInterpretability research company building tools to understand and edit the internal workings of neural networks.InterpretabilitySee siteHN 3

SHAPshap.readthedocs.ioGame-theoretic approach to explaining the output of any machine learning model using Shapley values.InterpretabilityOpen source★ 25.8k

Captumcaptum.aiPyTorch library for model interpretability with integrated gradients, saliency and other attribution methods.InterpretabilityOpen source★ 5.7k

TransformerLensgithub.comLibrary for mechanistic interpretability that exposes and edits the internal activations of GPT-style models.InterpretabilityOpen source★ 3.9k