Analysis of Variational Sparse Autoencoders

• URL: http://arxiv.org/abs/2509.22994v2
• Date: Wed, 01 Oct 2025 20:44:58 GMT
• Title: Analysis of Variational Sparse Autoencoders
• Abstract summary: 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.
• Score: 1.675385127117872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational methods into SAE architectures can improve feature organization and interpretability. We introduce the Variational Sparse Autoencoder (vSAE), which replaces deterministic ReLU gating with stochastic sampling from learned Gaussian posteriors and incorporates KL divergence regularization toward a standard normal prior. Our hypothesis is that this probabilistic sampling creates dispersive pressure, causing features to organize more coherently in the latent space while avoiding overlap. We evaluate a TopK vSAE against a standard TopK SAE on Pythia-70M transformer residual stream activations using comprehensive benchmarks including SAE Bench, individual feature interpretability analysis, and global latent space visualization through t-SNE. The vSAE underperforms standard SAE across core evaluation metrics, though excels at feature independence and ablation metrics. The KL divergence term creates excessive regularization pressure that substantially reduces the fraction of living features, leading to observed performance degradation. While vSAE features demonstrate improved robustness, they exhibit many more dead features than baseline. Our findings suggest that naive application of variational methods to SAEs does not improve feature organization or interpretability.

Related papers

• When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs [15.418870425179875]
  Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models.<n>We show that for a fixed SAE, its impact is governed by perturbation energy.<n>We propose a layer-wise sparsity allocation strategy, achieving lower perplexity under the same average pruning sparsity.
  arXiv  Detail & Related papers  (2026-08-26T15:57:42Z)
• From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability [53.681678236115836]
  We study when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM.<n>Our framework derives an upper bound on the base model's expected risk using four measurable quantities.<n>We show that the bound becomes non-vacuous on GPT-2 Small, Gemma-2B, and Llama-3-8B at practical sample sizes.
  arXiv  Detail & Related papers  (2026-06-16T18:28:23Z)
• Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders [7.5916620727820225]
  Sparse autoencoders (SAEs) are widely used to interpret neural network representations.<n>We study this question through emphfeature stability: for each SAE feature, we estimate the probability that a similar feature reappears in an independently trained SAE.<n>We find a pronounced functional asymmetry: stable features carry most of the reconstruction- and prediction-relevant signal, while unstable features have weak marginal impact.
  arXiv  Detail & Related papers  (2026-06-10T14:32:57Z)
• Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models [80.45129499188461]
  We introduce Qwen-Scope, an open-source suite of sparse autoencoders (SAEs) built on the Qwen model family.<n>We show that SAEs can go beyond post-hoc analysis to serve as practical interfaces for model development along four directions.
  arXiv  Detail & Related papers  (2026-05-12T10:01:06Z)
• Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders [20.13794189010598]
  Preference learning in large language models relies on reward models as proxies for human judgment.<n>We analyze this instability at the representation level under three semantic-preserving perturbation types.<n>We propose two SAE-based instability mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-07T16:48:48Z)
• Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection [4.496267803613718]
  We present the first application of SAEs to the ViT [] token for out-of-distribution (OOD) detection.<n>Our findings demonstrate that the sparse, disentangled features revealed by SAEs can serve as a powerful, interpretable tool for robust OOD detection in vision models.
  arXiv  Detail & Related papers  (2026-04-29T08:23:38Z)
• Feature-Space Adversarial Robustness Certification for Multimodal Large Language Models [59.6491828112519]
  Multimodal large language models (MLLMs) exhibit strong capabilities across diverse applications.<n> MLLMs are vulnerable to adversarial perturbations that distort their feature representations and induce erroneous predictions.<n>We propose Feature-space Smoothing (FS), a general framework that provides certified robustness guarantees at the feature representation level of MLLMs.
  arXiv  Detail & Related papers  (2026-01-22T18:52:21Z)
• Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection [62.89126207012712]
  Face Presentation Attack Detection (PAD) demands incremental learning to combat spoofing tactics and domains.<n>Privacy regulations forbid retaining past data, necessitating rehearsal-free learning (RF-IL)
  arXiv  Detail & Related papers  (2025-12-22T04:30:11Z)
• ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders [30.219733023958188]
  Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models.<n>We propose a semantically-guided SAE, called ProtSAE.<n>We show that ProtSAE learns more biologically relevant and interpretable hidden features compared to previous methods.
  arXiv  Detail & Related papers  (2025-08-26T11:20:31Z)
• 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)
• Probabilistic Variational Contrastive Learning [2.512491726995032]
  We propose a decoder-free framework that maximizes the evidence lower bound (ELBO)<n>We model the approximate posterior $q_theta(z|x)$ as a projected normal distribution, enabling the sampling of probabilistic embeddings.
  arXiv  Detail & Related papers  (2025-06-11T20:26:07Z)
• Ensembling Sparse Autoencoders [10.81463830315253]
  Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features.<n>We propose to ensemble multiple SAEs through naive bagging and boosting.<n>Our empirical results demonstrate that ensembling SAEs can improve the reconstruction of language model activations, diversity of features, and SAE stability.
  arXiv  Detail & Related papers  (2025-05-21T23:31:21Z)
• Do Sparse Autoencoders Generalize? A Case Study of Answerability [32.356991861926105]
  We evaluate SAE feature generalization across diverse, partly self-constructed answerability datasets for Gemma 2 SAEs.<n>Our analysis reveals that residual stream probes outperform SAE features within domains, but generalization performance differs sharply.
  arXiv  Detail & Related papers  (2025-02-27T10:45:25Z)
• Source-Free Domain Adaptive Object Detection with Semantics Compensation [54.00183496587841]
  We introduce Weak-to-strong Semantics Compensation (WSCo) for strong data augmentation.<n>WSCo compensates for the class-relevant semantics that may be lost during strong augmentation on the fly.<n>WSCo can be implemented as a generic plug-in, easily integrable with any existing SFOD pipelines.
  arXiv  Detail & Related papers  (2024-10-07T23:32:06Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE enhances global feature representation of point cloud masked autoencoders by making them both discriminative and sensitive to transformations.<n>We propose a novel loss that explicitly penalizes invariant collapse, enabling the network to capture richer transformation cues while preserving discriminative representations.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach [51.012396632595554]
  Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments. Recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. We develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects.
  arXiv  Detail & Related papers  (2023-12-15T12:58:05Z)
• An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization [52.44068740462729]
  We present an information-theoretic perspective on the VICReg objective. We derive a generalization bound for VICReg, revealing its inherent advantages for downstream tasks. We introduce a family of SSL methods derived from information-theoretic principles that outperform existing SSL techniques.
  arXiv  Detail & Related papers  (2023-03-01T16:36:25Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)

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.