Navigating the Concept Space of Language Models
Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting top-activating examples, manually browsing individual features, or performing semantic search on interested concepts, which makes exploratory discovery of concepts difficult at scale. In this paper, we present Concept Explorer, a scalable interactive system for post-hoc exploration of SAE features that organizes concept explanations using hierarchical neighborhood embeddings. Our approach constructs a multi-resolution manifold over SAE feature embeddings and enables progressive navigation from coarse concept clusters to fine-grained neighborhoods, supporting discovery, comparison, and relationship analysis among concepts. We demonstrate the utility of Concept Explorer on SAE features extracted from SmolLM2, where it reveals coherent high-level structure, meaningful subclusters, and distinctive rare concepts that are hard to identify with existing workflows.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Navigating the Conceptual Multiverse
When language models answer open-ended problems, they implicitly make hidden decisions that shape their outputs, leaving users with uncontextualized answers rather than a working map of the problem; drawing on multiverse…
Navigating Conceptual Space; A new take on Artificial General Intelligence
Edward C. Tolman found reinforcement learning unsatisfactory for explaining intelligence and proposed a clear distinction between learning and behavior. Tolman's ideas on latent learning and cognitive maps eventually led…
Autonomous NavigationRobot NavigationvalidNavigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space. Commonly, CA…
TAGAI-as-exploration: Navigating intelligence space
Artificial Intelligence is a field that lives many lives, and the term has come to encompass a motley collection of scientific and commercial endeavours. In this paper, I articulate the contours of a rather neglected but…
Mixture of Concept Bottleneck Experts
Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically constrain their task predictor to a single expression whose functional…