Bilinear autoencoders find interpretable manifolds

• URL: http://arxiv.org/abs/2605.08891v1
• Date: Sat, 09 May 2026 11:16:34 GMT
• Title: Bilinear autoencoders find interpretable manifolds
• Abstract summary: We implement quadratic latents with bilinear autoencoders, which decompose activations into low-rank quadratic forms, compose linearly in weight space, and admit input-independent geometric analysis.<n>Our experiments and visualisations show that multi-dimensional geometries are highly prevalent and that composite latents capture them well.<n> Practically, these models serve as an unsupervised tool for manifold discovery, which we demonstrate through an interactive online visualizer for Qwen 3.5.
• Score: 0.6999740786886536
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span manifolds that current linear methods cannot capture without post hoc analysis. This paper uses quadratic latents to close this gap: we implement these with bilinear autoencoders, which decompose activations into low-rank quadratic forms, compose linearly in weight space, and admit input-independent geometric analysis. This qualitative difference in what concepts quadratic latents can detect challenges the standard linear representation hypothesis. Our experiments and visualisations show that multi-dimensional geometries are highly prevalent and that composite latents capture them well, systematically improving reconstruction error in language models. Furthermore, we show that autoencoders with varying geometric priors recover the same input subspace despite their dictionary entries being distinct. Practically, these models serve as an unsupervised tool for manifold discovery, which we demonstrate through an interactive online visualizer for Qwen 3.5. This is a step toward nonlinear but mathematically tractable latent representations whose composition is expressive and interpretable by design.

Related papers

• Finding Manifolds With Bilinear Autoencoders [0.8594140167290097]
  Polynomials serve as primitives that can be analysed without reference to input.<n>We discuss improvements that induce importance ordering, clustering, and activation sparsity.<n>This is an initial step toward analysable latents through their properties.
  arXiv  Detail & Related papers  (2025-10-19T13:17:14Z)
• The Origins of Representation Manifolds in Large Language Models [52.68554895844062]
  We show that cosine similarity in representation space may encode the intrinsic geometry of a feature through shortest, on-manifold paths.<n>The critical assumptions and predictions of the theory are validated on text embeddings and token activations of large language models.
  arXiv  Detail & Related papers  (2025-05-23T13:31:22Z)
• Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation [85.82112629564942]
  We propose TokenBridge, which maintains the strong representation capacity of continuous tokens while preserving the modeling simplicity of discrete tokens.<n>We introduce a dimension-wise quantization strategy that independently discretizes each feature dimension, paired with a lightweight autoregressive prediction mechanism.<n>Our approach achieves reconstruction and generation quality on par with continuous methods while using standard categorical prediction.
  arXiv  Detail & Related papers  (2025-03-20T17:59:59Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Posterior Collapse and Latent Variable Non-identifiability [54.842098835445]
  We propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility. Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.
  arXiv  Detail & Related papers  (2023-01-02T06:16:56Z)
• Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders [45.29194877564103]
  This work introduces a chart autoencoder with an asymmetric encoding-decoding process that can incorporate additional semi-supervised information such as class labels. We discuss the approximation power of such networks and derive a bound that essentially depends on the intrinsic dimension of the data manifold rather than the dimension of ambient space.
  arXiv  Detail & Related papers  (2022-08-22T19:58:03Z)
• The Low-Dimensional Linear Geometry of Contextualized Word Representations [27.50785941238007]
  We study the linear geometry of contextualized word representations in ELMO and BERT. We show that a variety of linguistic features are encoded in low-dimensional subspaces.
  arXiv  Detail & Related papers  (2021-05-15T00:58:08Z)
• Autoencoder Image Interpolation by Shaping the Latent Space [12.482988592988868]
  Autoencoders represent an effective approach for computing the underlying factors characterizing datasets of different types. We propose a regularization technique that shapes the latent representation to follow a manifold consistent with the training images.
  arXiv  Detail & Related papers  (2020-08-04T12:32:54Z)
• Learning Bijective Feature Maps for Linear ICA [73.85904548374575]
  We show that existing probabilistic deep generative models (DGMs) which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. We create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
  arXiv  Detail & Related papers  (2020-02-18T17:58:07Z)

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.