shuyhere / Awesome-Sparse-Autoencoder
Collection of Reverse Engineering in Large Model
☆30Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for Awesome-Sparse-Autoencoder
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆45Updated 7 months ago
- ☆72Updated 4 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆29Updated 6 months ago
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆13Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆119Updated last month
- The Paper List on Data Contamination for Large Language Models Evaluation.☆75Updated this week
- ☆81Updated last year
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆174Updated last month
- Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆26Updated 2 weeks ago
- A resource repository for representation engineering in large language models☆54Updated this week
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆25Updated 4 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆58Updated 8 months ago
- AI Logging for Interpretability and Explainability🔬☆89Updated 5 months ago
- ☆54Updated 2 months ago
- ☆26Updated 6 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆48Updated this week
- This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers…☆52Updated last week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆54Updated 2 weeks ago
- ☆71Updated 3 months ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆75Updated last month
- Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (ACL 2024)☆50Updated 6 months ago
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆62Updated last month
- The official repository of the Omni-MATH benchmark.☆49Updated 2 weeks ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆97Updated 7 months ago
- ☆39Updated last year
- ☆20Updated last year
- Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆26Updated 3 weeks ago
- ☆98Updated 3 months ago
- Using sparse coding to find distributed representations used by neural networks.☆184Updated last year
- ☆36Updated 3 months ago