hannamw / eap-ig-faithfulnessLinks
Code for "Automatic Circuit Finding and Faithfulness"
☆14Updated last year
Alternatives and similar repositories for eap-ig-faithfulness
Users that are interested in eap-ig-faithfulness are comparing it to the libraries listed below
Sorting:
- ☆57Updated 3 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆83Updated 7 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆42Updated 9 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 9 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆66Updated 11 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆76Updated last year
- [ICLR 2025] General-purpose activation steering library☆114Updated last month
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆33Updated last year
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆45Updated 11 months ago
- A resource repository for representation engineering in large language models☆139Updated 11 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆29Updated last year
- ☆56Updated 2 years ago
- ☆191Updated 2 weeks ago
- ☆98Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆191Updated last year
- ☆66Updated last year
- ☆63Updated 7 months ago
- awesome SAE papers☆54Updated 5 months ago
- ☆48Updated 2 years ago
- Function Vectors in Large Language Models (ICLR 2024)☆181Updated 6 months ago
- Sparse probing paper full code.☆62Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆116Updated 8 months ago
- ☆51Updated last year
- ☆181Updated 11 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆41Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- ☆234Updated last year