Scaling and evaluating sparse autoencoders
By Leo Gao, Tom Dupr'e la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu. International Conference on Learning Representations, 2024
535 citations recorded by the source corpus.
Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders need to be very large to recover all relevant features. However, studying the properties of autoencoder scaling is difficult due to the need to balance reconstruction and sparsity objectives and the presence of dead latents. We propose using k-sparse autoencoders [Makhzani and Frey, 2013] to directly control sparsity, simplifying tuning and improving the reconstruction-sparsity frontier. Additionally, we find modifications that result in few dead latents, even at the largest scales we tried. Using these techniques, we find clean scaling laws with respect to autoencoder size and sparsity. We also introduce several new metrics for evaluating feature quality based on the recovery of hypothesized features, the explainability of activation patterns, and the sparsity of downstream effects. These metrics all generally improve with autoencoder size. To demonstrate the scalability of our approach, we train a 16 million latent autoencoder on GPT-4 activations for 40 billion tokens. We release training code and autoencoders for open-source models, as well as a visualizer.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/0d24c5680efe9769e6d7ea579db0499ec819a8c7
Citations in the corpus
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models (2024, unknown): “Scalably training better SAEs is an active area of research, as illustrated by the ready availability of open-source SAEs (Gao et al., 2024; Lieberum et al., 2024; Lin & Bloom, 2023).”
- Sparse Prototype Code Underlies Classification and Prediction Across Modalities (2026, unknown): “…seek low-dimensional, semantically meaningful directions in activations [Makhzani and Frey, 2013, Huben et al., 2024, Templeton et al., 2026, Gao et al., 2025]; our results identify a complementary sparse class-supervised set of directions whose functional role is directly tied to…”
- Navigating the Concept Space of Language Models (2026, unknown): “Contemporary SAEs frequently contain hundreds of thousands to millions of latent dimensions (Templeton et al., 2024; Gao et al., 2025).”