Navigating the Concept Space of Language Models
This work addresses the challenge of scalable concept discovery for researchers analyzing language model interpretability, though it is incremental as it builds on existing sparse autoencoder methods.
The paper tackles the problem of exploring sparse autoencoder features from language models, which is difficult with current manual methods, by presenting Concept Explorer, a scalable interactive system that organizes concepts hierarchically and enables navigation from coarse clusters to fine-grained neighborhoods, demonstrating its utility on SmolLM2 features to reveal coherent structure and rare concepts.
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.