Representation Engineering: A Top-Down Approach to AI Transparency
☆1,010Aug 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Improving Alignment and Robustness with Circuit Breakers☆264Sep 24, 2024Updated last year
- A library for making RepE control vectors☆738Sep 24, 2025Updated 9 months ago
- A resource repository for representation engineering in large language models☆154Nov 14, 2024Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆581Jan 28, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆262Feb 27, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A library for mechanistic interpretability of GPT-style language models☆3,603Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆153Feb 21, 2025Updated last year
- ☆253Feb 22, 2024Updated 2 years ago
- ☆219Oct 14, 2025Updated 8 months ago
- Algebraic value editing in pretrained language models☆70Nov 1, 2023Updated 2 years ago
- ☆290Oct 1, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆888Mar 6, 2026Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆237May 23, 2024Updated 2 years ago
- Using sparse coding to find distributed representations used by neural networks.☆307Nov 10, 2023Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Training Sparse Autoencoders on Language Models☆1,442Jun 24, 2026Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆302Jul 20, 2024Updated last year
- ☆287Mar 2, 2024Updated 2 years ago
- ☆590Jul 19, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆598Aug 7, 2025Updated 10 months ago
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆991Aug 16, 2024Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆412Jun 13, 2025Updated last year
- Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)☆123Feb 11, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆971Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆89Mar 7, 2025Updated last year
- ☆1,083Mar 6, 2024Updated 2 years ago
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,571Mar 5, 2026Updated 3 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆118Jun 13, 2024Updated 2 years ago
- Sparse Autoencoder Training Library☆57May 1, 2025Updated 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.☆91May 19, 2024Updated 2 years ago
- Universal and Transferable Attacks on Aligned Language Models☆4,714Aug 2, 2024Updated last year
- ☆111Aug 8, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- 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…☆356Feb 23, 2024Updated 2 years ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆388Jan 23, 2025Updated last year
- ☆4,120Apr 15, 2026Updated 2 months ago
- Must-read Papers on Knowledge Editing for Large Language Models.☆1,235Updated this week
- [ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.…☆28Sep 25, 2024Updated last year
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆33Jul 31, 2025Updated 11 months ago
- Erasing concepts from neural representations with provable guarantees☆256Jan 27, 2025Updated last year