A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders

• URL: http://arxiv.org/abs/2606.07007v1
• Date: Fri, 05 Jun 2026 07:52:43 GMT
• Title: A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders
• Abstract summary: We formalize concepts as sets of data points and cast concept learning as a set-alignment problem between human-defined and model-induced concepts.<n>This formulation distinguishes three increasingly strong notions of learning -- detection, separation, and approximation.<n>It also yields geometric conditions, error bounds, and capacity constraints for when concepts can be represented by individual neurons or multi-neuron units.
• Score: 17.913861279194663
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs). While SAEs improve interpretability of neural networks by learning sparse feature representations, a principled definition of ''concept'' and ''learning'' remains unclear. We formalize concepts as sets of data points and cast concept learning as a set-alignment problem between human-defined and model-induced concepts. This formulation distinguishes three increasingly strong notions of learning -- detection, separation, and approximation -- and yields geometric conditions, error bounds, and capacity constraints for when concepts can be represented by individual neurons or multi-neuron units. It also provides a set-theoretic account for common SAE phenomena, including feature splitting, feature absorption, feature families, and hierarchical concepts. Finally, we connect concept learning and neuron interpretation through formal concept analysis, showing that the two directions need not agree and that their many-to-many structure can be organized by concept lattices. Experiments on synthetic data with ReLU and Top-$K$ SAEs illustrate the theory and reveal the effects of SAE size and sparsity on concept learning.

Related papers

• Concept frustration: Aligning human concepts and machine representations [39.50576817657001]
  We introduce a framework for comparing supervised human concepts with unsupervised intermediate representations extracted from foundation model embeddings.<n>Motivated by the role of conceptual leaps in scientific discovery, we formalise the notion of concept frustration.<n>We develop task-aligned similarity measures that detect concept frustration between supervised concept-based models and unsupervised representations.
  arXiv  Detail & Related papers  (2026-03-31T12:17:21Z)
• A Geometric Unification of Concept Learning with Concept Cones [58.70836885177496]
  Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs) and Sparse Autoencoders (SAEs)<n>We show that both paradigms instantiate the same geometric structure.<n>CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs.
  arXiv  Detail & Related papers  (2025-12-08T09:51:46Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• 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)
• Nonparametric Identification of Latent Concepts [17.996329262929113]
  We argue that the cognitive mechanism of comparison, fundamental to human learning, is also vital for machines to recover true concepts underlying the data.<n>Specifically, we aim to develop a theoretical framework for the identifiability of concepts with multiple classes of observations.<n>We show that with sufficient diversity across classes, hidden concepts can be identified without assuming specific concept types.
  arXiv  Detail & Related papers  (2025-09-30T18:13:53Z)
• Neuro-Symbolic Concepts [72.94541757514396]
  This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly.<n>The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts.<n>This framework offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.
  arXiv  Detail & Related papers  (2025-05-09T17:02:51Z)
• Revealing emergent human-like conceptual representations from language prediction [90.73285317321312]
  Large language models (LLMs) trained solely through next-token prediction on text exhibit strikingly human-like behaviors.<n>Are these models developing concepts akin to those of humans?<n>We found that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts.
  arXiv  Detail & Related papers  (2025-01-21T23:54:17Z)
• LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions [15.381209058506078]
  Prior works have associated concepts with neurons based on examples of concepts or a pre-defined set of concepts. We propose to leverage multimodal large language models for automatic and open-ended concept discovery. We validate each concept by generating examples and counterexamples and evaluating the neuron's response on this new set of images.
  arXiv  Detail & Related papers  (2024-06-12T18:19:37Z)
• Do Concept Bottleneck Models Respect Localities? [14.77558378567965]
  Concept-based explainability methods use human-understandable intermediaries to produce explanations for machine learning models.<n>We assess whether concept predictors leverage "relevant" features to make predictions, a term we call locality.<n>We find that many concept-based models used in practice fail to respect localities because concept predictors cannot always clearly distinguish distinct concepts.
  arXiv  Detail & Related papers  (2024-01-02T16:05:23Z)
• Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
  We introduce concept explanations including the class of Concept Activation Vectors (CAV) We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
  arXiv  Detail & Related papers  (2022-02-25T01:27:31Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Formalising Concepts as Grounded Abstractions [68.24080871981869]
  This report shows how representation learning can be used to induce concepts from raw data. The main technical goal of this report is to show how techniques from representation learning can be married with a lattice-theoretic formulation of conceptual spaces.
  arXiv  Detail & Related papers  (2021-01-13T15:22:01Z)

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.