paper-with-me

Papers

Efficient Dictionary Learning with Switch Sparse Autoencoders

2024-10-10 · Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schroeder de Witt

Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to scale them up to very high width, posing a computational challenge. In this work, we introduce Switch Sparse Autoencoders, a novel SAE architecture aimed at reducing the compute cost of training SAEs. Inspired by sparse mixture of experts models, Switch SAEs route activation vectors between smaller "expert" SAEs, enabling SAEs to efficiently scale to many more features. We present experiments comparing Switch SAEs with other SAE architectures, and find that Switch SAEs deliver a substantial Pareto improvement in the reconstruction vs. sparsity frontier for a given fixed training compute budget. We also study the geometry of features across experts, analyze features duplicated across experts, and verify that Switch SAE features are as interpretable as features found by other SAE architectures.

📄 PDF Abstract BibTeX arXiv:2410.08201

Code (1)

amudide/switch_sae 공식 구현 pytorch

Tasks

Dictionary LearningMixture-of-Experts

Similar Papers 제목 키워드 기반

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation

2026-08-13 · Valentin Noël arxiv

Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see what changes. But a latent fires at many tokens, and the effect has…

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation

2026-03-30 · Vitória Barin Pacela, Shruti Joshi, Isabela Camacho, Simon Lacoste-Julien 외 arxiv

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept spa…

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning

2025-05-30 · Stepan Shabalin, Ayush Panda, Dmitrii Kharlapenko, Abdur Raheem Ali 외

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diff…

Dictionary LearningImage GenerationLanguage ModelingLanguage Modelling

Sparse Coding with Multi-Layer Decoders using Variance Regularization

2021-12-16 · Katrina Evtimova, Yann Lecun

Sparse representations of images are useful in many computer vision applications. Sparse coding with an $l_1$ penalty and a learned linear dictionary requires regularization of the dictionary to prevent a collapse in the…

DecoderDenoising

Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning

2019-04-18 · Bahareh Tolooshams, Sourav Dey, Demba Ba

We introduce a neural-network architecture, termed the constrained recurrent sparse autoencoder (CRsAE), that solves convolutional dictionary learning problems, thus establishing a link between dictionary learning and ne…

DenoisingDictionary LearningImage Denoising