domains / families / research / saelens

saelens

separate

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.

When to use

• Discover interpretable features in model activations
• Understand what concepts a model has learned
• Study superposition and feature geometry
• Perform feature-based steering or ablation
• Analyze safety-relevant features (deception, bias, harmful content)
• You need basic activation analysis → Use **TransformerLens** directly
• You want causal intervention experiments → Use **pyvene** or **TransformerLens**
• You need production steering → Consider direct activation engineering

When not to use

• Basic activation analysis
• Causal intervention experiments
• Production steering

Skill page

Source