A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918146072379392 |
|---|---|
| author | Shu, Dong Wu, Xuansheng Zhao, Haiyan Rai, Daking Yao, Ziyu Liu, Ninghao Du, Mengnan |
| author_facet | Shu, Dong Wu, Xuansheng Zhao, Haiyan Rai, Daking Yao, Ziyu Liu, Ninghao Du, Mengnan |
| contents | Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a means to understand the inner workings of LLMs. Among various mechanistic interpretability approaches, Sparse Autoencoders (SAEs) have emerged as a promising method due to their ability to disentangle the complex, superimposed features within LLMs into more interpretable components. This paper presents a comprehensive survey of SAEs for interpreting and understanding the internal workings of LLMs. Our major contributions include: (1) exploring the technical framework of SAEs, covering basic architecture, design improvements, and effective training strategies; (2) examining different approaches to explaining SAE features, categorized into input-based and output-based explanation methods; (3) discussing evaluation methods for assessing SAE performance, covering both structural and functional metrics; and (4) investigating real-world applications of SAEs in understanding and manipulating LLM behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05613 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models Shu, Dong Wu, Xuansheng Zhao, Haiyan Rai, Daking Yao, Ziyu Liu, Ninghao Du, Mengnan Machine Learning Artificial Intelligence Computation and Language Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a means to understand the inner workings of LLMs. Among various mechanistic interpretability approaches, Sparse Autoencoders (SAEs) have emerged as a promising method due to their ability to disentangle the complex, superimposed features within LLMs into more interpretable components. This paper presents a comprehensive survey of SAEs for interpreting and understanding the internal workings of LLMs. Our major contributions include: (1) exploring the technical framework of SAEs, covering basic architecture, design improvements, and effective training strategies; (2) examining different approaches to explaining SAE features, categorized into input-based and output-based explanation methods; (3) discussing evaluation methods for assessing SAE performance, covering both structural and functional metrics; and (4) investigating real-world applications of SAEs in understanding and manipulating LLM behaviors. |
| title | A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.05613 |