Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders

• URL: http://arxiv.org/abs/2511.09432v1
• Date: Thu, 13 Nov 2025 01:54:03 GMT
• Title: Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders
• Authors: Ege Erdogan, Ana Lucic,
• Abstract summary: Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks.<n>We show that incorporating such group symmetries into the SAEs yields features more useful in downstream tasks.
• Score: 3.7894019466201274
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as scientific data with group symmetries, introduces challenges that can hinder their effectiveness. We show that incorporating such group symmetries into the SAEs yields features more useful in downstream tasks. More specifically, we train autoencoders on synthetic images and find that a single matrix can explain how their activations transform as the images are rotated. Building on this, we develop adaptively equivariant SAEs that can adapt to the base model's level of equivariance. These adaptive SAEs discover features that lead to superior probing performance compared to regular SAEs, demonstrating the value of incorporating symmetries in mechanistic interpretability tools.

Related papers

• Analysis of Variational Sparse Autoencoders [1.675385127117872]
  We investigate whether incorporating variational methods into SAE architectures can improve feature organization and interpretability.<n>We introduce the Variational Sparse Autoencoder (vSAE), which replaces deterministic ReLU gating with sampling from learned Gaussian posteriors.<n>Our findings suggest that naive application of variational methods to SAEs does not improve feature organization or interpretability.
  arXiv  Detail & Related papers  (2025-09-26T23:09:56Z)
• Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders [50.52694757593443]
  Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations.<n>We first propose a novel statistical framework for the feature recovery problem, which includes a new notion of feature identifiability.<n>We introduce a new SAE training algorithm based on bias adaptation'', a technique that adaptively adjusts neural network bias parameters to ensure appropriate activation sparsity.
  arXiv  Detail & Related papers  (2025-06-16T20:58:05Z)
• Approximate Equivariance in Reinforcement Learning [35.04248486334824]
  We develop approximately equivariant algorithms in reinforcement learning.<n>Results show that the approximately equivariant network performs on par with exactly equivariant networks when exact symmetries are present.
  arXiv  Detail & Related papers  (2024-11-06T19:44:46Z)
• Learning Layer-wise Equivariances Automatically using Gradients [66.81218780702125]
  Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. symmetries provide fixed hard constraints on the functions a network can represent, need to be specified in advance, and can not be adapted. Our goal is to allow flexible symmetry constraints that can automatically be learned from data using gradients.
  arXiv  Detail & Related papers  (2023-10-09T20:22:43Z)
• Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance [16.49488981364657]
  We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. We use an arbitrary base model such as anvariant or a transformer and symmetrize it to be equivariant to the given group. Empirical tests show competitive results against tailored equivariant architectures.
  arXiv  Detail & Related papers  (2023-06-05T13:40:54Z)
• Self-Supervised Learning for Group Equivariant Neural Networks [75.62232699377877]
  Group equivariant neural networks are the models whose structure is restricted to commute with the transformations on the input. We propose two concepts for self-supervised tasks: equivariant pretext labels and invariant contrastive loss. Experiments on standard image recognition benchmarks demonstrate that the equivariant neural networks exploit the proposed self-supervised tasks.
  arXiv  Detail & Related papers  (2023-03-08T08:11:26Z)
• Lorentz group equivariant autoencoders [6.858459233149096]
  Lorentz group autoencoder (LGAE) We develop an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group $mathrmSO+(2,1)$, with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics.
  arXiv  Detail & Related papers  (2022-12-14T17:19:46Z)
• Learning Symmetric Embeddings for Equivariant World Models [9.781637768189158]
  We propose learning symmetric embedding networks (SENs) that encode an input space (e.g. images) This network can be trained end-to-end with an equivariant task network to learn an explicitly symmetric representation. Our experiments demonstrate that SENs facilitate the application of equivariant networks to data with complex symmetry representations.
  arXiv  Detail & Related papers  (2022-04-24T22:31:52Z)
• Topographic VAEs learn Equivariant Capsules [84.33745072274942]
  We introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. We demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
  arXiv  Detail & Related papers  (2021-09-03T09:25:57Z)
• Group Equivariant Subsampling [60.53371517247382]
  Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions. We first introduce translation equivariant subsampling/upsampling layers that can be used to construct exact translation equivariant CNNs. We then generalise these layers beyond translations to general groups, thus proposing group equivariant subsampling/upsampling.
  arXiv  Detail & Related papers  (2021-06-10T16:14:00Z)
• Meta-Learning Symmetries by Reparameterization [63.85144439337671]
  We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data. Our experiments suggest that it can automatically learn to encode equivariances to common transformations used in image processing tasks.
  arXiv  Detail & Related papers  (2020-07-06T17:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.