zepingyu0512 / awesome-SAELinks
awesome SAE papers
☆51Updated 5 months ago
Alternatives and similar repositories for awesome-SAE
Users that are interested in awesome-SAE are comparing it to the libraries listed below
Sorting:
- ☆31Updated 4 months ago
- A curated list of resources for activation engineering☆107Updated 3 weeks ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆45Updated 11 months ago
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆273Updated 7 months ago
- A resource repository for representation engineering in large language models☆138Updated 11 months ago
- ☆37Updated 10 months ago
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆118Updated 2 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆66Updated 11 months ago
- [EMNLP 2024] The official GitHub repo for the survey paper "Knowledge Conflicts for LLMs: A Survey"☆139Updated last year
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆80Updated 10 months ago
- ☆63Updated 7 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆121Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆42Updated 9 months ago
- LLM Unlearning☆176Updated 2 years ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆83Updated last year
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- ☆179Updated last year
- [ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"☆45Updated 2 weeks ago
- This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers…☆92Updated 10 months ago
- ☆17Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆85Updated 6 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆117Updated last year
- 📜 Paper list on decoding methods for LLMs and LVLMs☆61Updated 3 months ago
- [ACL 2024] Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models☆57Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆82Updated 7 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆26Updated last year
- [ACL'2024 Findings] "Understanding and Patching Compositional Reasoning in LLMs"☆12Updated last year
- A Survey on Data Selection for Language Models☆250Updated 5 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆31Updated 7 months ago
- Code for the ACL-2022 paper "Knowledge Neurons in Pretrained Transformers"☆171Updated last year