home/categories/machine-learning/davila7-claude-code-templates-cli-tool-components-skills-ai-research-mechanistic-interpretability-saelens-skill-md
machine-learningdata-ai
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.
maintainer
davila7
Обновлено 1/20/2026
Звёзды
17577
Форки
1576
quick start
Installation and usage
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.
Установка
$ install --globalskills.sh
Использование
После установки вы можете использовать этот skill, выполнив следующую команду в терминале:
skills use sparse-autoencoder-training