Representation Engineering: A Top-Down Approach to AI Transparency
☆965Aug 14, 2024Updated last year
Alternatives and similar repositories for representation-engineering
Users that are interested in representation-engineering are comparing it to the libraries listed below
Sorting:
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- A library for making RepE control vectors☆695Sep 24, 2025Updated 5 months ago
- A resource repository for representation engineering in large language models☆149Nov 14, 2024Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆573Jan 28, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆251Feb 27, 2026Updated 3 weeks ago
- A library for mechanistic interpretability of GPT-style language models☆3,183Mar 13, 2026Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Feb 21, 2025Updated last year
- ☆251Feb 22, 2024Updated 2 years ago
- ☆210Oct 14, 2025Updated 5 months ago
- ☆278Oct 1, 2024Updated last year
- Algebraic value editing in pretrained language models☆69Nov 1, 2023Updated 2 years ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆868Mar 6, 2026Updated 2 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆214May 23, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆298Nov 10, 2023Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,261Mar 14, 2026Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆294Jul 20, 2024Updated last year
- ☆578Jul 19, 2024Updated last year
- ☆283Mar 2, 2024Updated 2 years ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆879Aug 16, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆574Aug 7, 2025Updated 7 months ago
- ☆119Feb 11, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆361Jun 13, 2025Updated 9 months ago
- ☆1,073Mar 6, 2024Updated 2 years ago
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,564Mar 5, 2026Updated 2 weeks ago
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆116Jun 13, 2024Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90May 19, 2024Updated last year
- Universal and Transferable Attacks on Aligned Language Models☆4,568Aug 2, 2024Updated last year
- ☆104Aug 8, 2024Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆345Feb 23, 2024Updated 2 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆85Mar 7, 2025Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆380Jan 23, 2025Updated last year
- ☆4,112Jun 4, 2024Updated last year
- [ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.…☆28Sep 25, 2024Updated last year
- Erasing concepts from neural representations with provable guarantees☆245Jan 27, 2025Updated last year
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆26Jul 31, 2025Updated 7 months ago
- Must-read Papers on Knowledge Editing for Large Language Models.☆1,220Jul 12, 2025Updated 8 months ago