A library for making RepE control vectors
☆689Sep 24, 2025Updated 5 months ago
Alternatives and similar repositories for repeng
Users that are interested in repeng are comparing it to the libraries listed below
Sorting:
- Representation Engineering: A Top-Down Approach to AI Transparency☆953Aug 14, 2024Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆139Feb 21, 2025Updated last year
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆270Jan 10, 2026Updated last month
- Sparsify transformers with SAEs and transcoders☆696Updated this week
- ☆338Jul 28, 2025Updated 7 months ago
- ☆30Aug 2, 2024Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆3,434Nov 13, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆863Jan 29, 2026Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆212May 23, 2024Updated last year
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,558Jan 14, 2026Updated last month
- A library for mechanistic interpretability of GPT-style language models☆3,112Updated this week
- Training code for Sparse Autoencoders on Embedding models☆39Feb 27, 2025Updated last year
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- Go ahead and axolotl questions☆11,335Updated this week
- Training Sparse Autoencoders on Language Models☆1,219Updated this week
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Jan 7, 2026Updated last month
- Customizable implementation of the self-instruct paper.☆1,049Mar 7, 2024Updated last year
- Structured Outputs☆13,456Feb 13, 2026Updated 2 weeks ago
- Tools for merging pretrained large language models.☆6,814Jan 26, 2026Updated last month
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆825Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆247Updated this week
- A resource repository for representation engineering in large language models☆148Nov 14, 2024Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆198Feb 13, 2025Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆180May 2, 2024Updated last year
- Multiversal tree writing interface for human-AI collaboration☆1,341Jun 28, 2024Updated last year
- ☆155Feb 16, 2026Updated 2 weeks ago
- Optimizing inference proxy for LLMs☆3,342Jan 28, 2026Updated last month
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆581Jun 11, 2024Updated last year
- command loom interface☆111Feb 8, 2025Updated last year
- Visualize the intermediate output of Mistral 7B☆385Jan 22, 2025Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,108Updated this week
- utilities for decoding deep representations (like sentence embeddings) back to text☆1,069Dec 27, 2025Updated 2 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆43Mar 21, 2024Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Apr 29, 2024Updated last year
- [ICLR 2025] General-purpose activation steering library☆144Sep 18, 2025Updated 5 months ago
- Erasing concepts from neural representations with provable guarantees☆243Jan 27, 2025Updated last year
- A Loom implementation in Obsidian☆326Mar 20, 2025Updated 11 months ago
- Merge Transformers language models by use of gradient parameters.☆214Aug 8, 2024Updated last year
- Experiments with representation engineering☆13Feb 28, 2024Updated 2 years ago