Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages
Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic nature makes it difficult to isolate language-specific units from cross-lingual representations. To address this, we explore sparse autoencoders (SAEs) for their ability to learn monosemantic features that represent concrete and abstract concepts across languages in LLMs. While some of these features are language-independent, the presence of language-specific features remains underexplored. In this work, we introduce SAE-LAPE, a method based on feature activation probability, to identify language-specific features within the feed-forward network. We find that many such features predominantly appear in the middle to final layers of the model and are interpretable. These features influence the model's multilingual performance and language output and can be used for language identification with performance comparable to fastText along with more interpretability. Our code and complete figures are available at https://github.com/LyzanderAndrylie/language-specific-features
Code (0)
등록된 구현이 없습니다.
Tasks
Language IdentificationSimilar Papers 제목 키워드 기반
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed acyclic graph over sparse, interpretable …
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangl…
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) …
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of le…
Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs
Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret. Sparse Autoencoders (SAEs) provide a scalab…