SAELens Reference Documentation

This directory contains comprehensive reference materials for SAELens.

Contents

• api.md - Complete API reference for SAE, TrainingSAE, and configuration classes
• tutorials.md - Step-by-step tutorials for training and analyzing SAEs

Quick Links

• GitHub Repository: https://github.com/jbloomAus/SAELens
• Neuronpedia: https://neuronpedia.org (browse pre-trained SAE features)
• HuggingFace SAEs: Search for tag saelens

Installation

pip install sae-lens

Requirements: Python 3.10+, transformer-lens>=2.0.0

Basic Usage

from transformer_lens import HookedTransformer
from sae_lens import SAE

# Load model and SAE
model = HookedTransformer.from_pretrained("gpt2-small", device="cuda")
sae, cfg_dict, sparsity = SAE.from_pretrained(
    release="gpt2-small-res-jb",
    sae_id="blocks.8.hook_resid_pre",
    device="cuda"
)

# Encode activations to sparse features
tokens = model.to_tokens("Hello world")
_, cache = model.run_with_cache(tokens)
activations = cache["resid_pre", 8]

features = sae.encode(activations)  # Sparse feature activations
reconstructed = sae.decode(features)  # Reconstructed activations

Key Concepts

Sparse Autoencoders

SAEs decompose dense neural activations into sparse, interpretable features:

• Encoder: Maps d_model → d_sae (typically 4-16x expansion)
• ReLU/TopK: Enforces sparsity
• Decoder: Reconstructs original activations

Training Loss

Loss = MSE(original, reconstructed) + L1_coefficient × L1(features)

Key Metrics

• L0: Average number of active features (target: 50-200)
• CE Loss Score: Cross-entropy recovered vs original model (target: 80-95%)
• Dead Features: Features that never activate (target: <5%)

Available Pre-trained SAEs