paper-with-me

Papers

Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages

2025-07-15 · Lyzander Marciano Andrylie, Inaya Rahmanisa, Mahardika Krisna Ihsani, Alfan Farizki Wicaksono, Haryo Akbarianto Wibowo, Alham Fikri Aji arxiv

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

📄 PDF Abstract BibTeX arXiv:2507.11230

Code (0)

등록된 구현이 없습니다.

Tasks

Language Identification

Similar Papers 제목 키워드 기반

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning

2026-03-11 · Md Muntaqim Meherab, Noor Islam S. Mohammad, Faiza Feroz arxiv

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

2024-11-01 · Aashiq Muhamed, Mona Diab, Virginia Smith

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

2025-10-30 · Usha Bhalla, Alex Oesterling, Claudio Mayrink Verdun, Himabindu Lakkaraju 외 arxiv

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

2025-03-21 · Bart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda

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

2026-06-15 · Yusong Zhao, Hengyi Wang, Tanuja Ganu, Akshay Nambi 외 arxiv

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…