Interpretable and Steerable Concept Bottleneck Sparse Autoencoders

• URL: http://arxiv.org/abs/2512.10805v1
• Date: Thu, 11 Dec 2025 16:48:07 GMT
• Title: Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
• Authors: Akshay Kulkarni, Tsui-Wei Weng, Vivek Narayanaswamy, Shusen Liu, Wesam A. Sakla, Kowshik Thopalli,
• Abstract summary: We introduce two new computationally inexpensive interpretability and steerability metrics and conduct a systematic analysis on LVLMs.<n>We propose Concept Bottleneck Sparse Autoencoders (CB-SAE) - a novel post-hoc framework that prunes low-utility neurons and augments the latent space with a lightweight concept bottleneck aligned to a user-defined concept set.<n>The resulting CB-SAE improves interpretability by +32.1% and steerability by +14.5% across LVLMs and image generation tasks.
• Score: 20.94500960067637
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires that the learned features be both interpretable and steerable. To that end, we introduce two new computationally inexpensive interpretability and steerability metrics and conduct a systematic analysis on LVLMs. Our analysis uncovers two observations; (i) a majority of SAE neurons exhibit either low interpretability or low steerability or both, rendering them ineffective for downstream use; and (ii) due to the unsupervised nature of SAEs, user-desired concepts are often absent in the learned dictionary, thus limiting their practical utility. To address these limitations, we propose Concept Bottleneck Sparse Autoencoders (CB-SAE) - a novel post-hoc framework that prunes low-utility neurons and augments the latent space with a lightweight concept bottleneck aligned to a user-defined concept set. The resulting CB-SAE improves interpretability by +32.1% and steerability by +14.5% across LVLMs and image generation tasks. We will make our code and model weights available.

Related papers

• Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs [51.378834857406325]
  Mechanistic interpretability seeks to mitigate the issues through extracts from large language models.<n>Sparse autoencoders (SAEs) have emerged as a popular approach for extracting interpretable and monosemantic concepts.<n>We show that SAEs suffer from a fundamental theoretical ambiguity: the well-defined correspondence between LLM representations and human-interpretable concepts remains unclear.
  arXiv  Detail & Related papers  (2026-01-28T09:27:05Z)
• Towards more holistic interpretability: A lightweight disentangled Concept Bottleneck Model [5.700536552863068]
  Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations.<n>We propose a lightweight Disentangled Concept Bottleneck Model (LDCBM) that automatically groups visual features into semantically meaningful components.<n> Experiments on three diverse datasets demonstrate that LDCBM achieves higher concept and class accuracy, outperforming previous CBMs in both interpretability and classification performance.
  arXiv  Detail & Related papers  (2025-10-17T15:59:30Z)
• CLMN: Concept based Language Models via Neural Symbolic Reasoning [27.255064617527328]
  Concept Language Model Network (CLMN) is a neural-symbolic framework that keeps both performance and interpretability.<n> CLMN represents concepts as continuous, human-readable embeddings.<n>Model augments original text features with concept-aware representations and automatically induces interpretable logic rules.
  arXiv  Detail & Related papers  (2025-10-11T06:58:44Z)
• 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)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models [50.587868616659826]
  We introduce a comprehensive framework for evaluating monosemanticity at the neuron-level in vision representations.<n>Our experimental results reveal that SAEs trained on Vision-Language Models significantly enhance the monosemanticity of individual neurons.
  arXiv  Detail & Related papers  (2025-04-03T17:58:35Z)
• Interpreting CLIP with Hierarchical Sparse Autoencoders [8.692675181549117]
  Matryoshka SAE (MSAE) learns hierarchical representations at multiple granularities simultaneously.<n>MSAE establishes a new state-of-the-art frontier between reconstruction quality and sparsity for CLIP.
  arXiv  Detail & Related papers  (2025-02-27T22:39:13Z)
• Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts [11.81523319216474]
  Steering methods manipulate the representations of large language models (LLMs) to induce responses that have desired properties.<n>Traditionally, steering has relied on supervision, such as from contrastive pairs of prompts that vary in a single target concept.<n>We introduce Sparse Shift Autoencoders (SSAEs) that instead map the differences between embeddings to sparse representations.
  arXiv  Detail & Related papers  (2025-02-14T08:49:41Z)
• AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders [73.37603699731329]
  We introduce AxBench, a large-scale benchmark for steering and concept detection.<n>For steering, we find that prompting outperforms all existing methods, followed by finetuning.<n>For concept detection, representation-based methods such as difference-in-means, perform the best.
  arXiv  Detail & Related papers  (2025-01-28T18:51:24Z)
• Interpretable Prognostics with Concept Bottleneck Models [5.939858158928473]
  Concept Bottleneck Models (CBMs) are inherently interpretable neural network architectures based on concept explanations. CBMs enable domain experts to intervene on the concept activations at test-time. Our case studies demonstrate that the performance of CBMs can be on par or superior to black-box models.
  arXiv  Detail & Related papers  (2024-05-27T18:15:40Z)
• Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention [53.896974148579346]
  Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. The enigmatic black-box'' nature of LLMs remains a significant challenge for interpretability, hampering transparent and accountable applications. We propose a novel methodology anchored in sparsity-guided techniques, aiming to provide a holistic interpretation of LLMs.
  arXiv  Detail & Related papers  (2023-12-22T19:55:58Z)

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.