Hermes Agent · Optional

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

MlopsOptionalv1.0.0MIT

What this skill is

This directory page tracks a Hermes-compatible skill reference and links back to the original source for install instructions, files, and updates.

Tags and platforms

Sparse AutoencodersSAEMechanistic InterpretabilityFeature DiscoverySuperposition

Featured

Your product here

Show your offer to OpenClaw operators and AI builders across every page and blog.

Advertise