Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)
☆132Feb 11, 2025Updated last year
Alternatives and similar repositories for linear_rep_geometry
Users that are interested in linear_rep_geometry are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for 'The Geometry of Categorical and Hierarchical Concepts in Large Language Models' (ICLR 2025, Oral)☆119Feb 11, 2025Updated last year
- ☆27Feb 9, 2023Updated 3 years ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- ☆428Aug 21, 2025Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆94Nov 27, 2024Updated last year
- 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.
- Code for 'The Information Geometry of Softmax: Probing and Steering' (ICML 2026)☆18May 19, 2026Updated 4 months ago
- ☆116Aug 8, 2024Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆163Feb 21, 2025Updated last year
- ☆26Jun 22, 2025Updated last year
- Code release for the paper "Style Vectors for Steering Generative Large Language Models", accepted to the Findings of the EACL 2024.☆37Sep 26, 2024Updated last year
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 5 months ago
- ☆60Jul 29, 2026Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆200Apr 30, 2026Updated 4 months ago
- ☆40Jul 9, 2025Updated 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.
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆899Mar 6, 2026Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆275Feb 27, 2026Updated 6 months ago
- ☆25Mar 30, 2026Updated 5 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,106Updated this week
- ☆297Oct 1, 2024Updated last year
- A resource repository for representation engineering in large language models☆155Nov 14, 2024Updated last year
- A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation☆16Aug 28, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆269Sep 24, 2024Updated last year
- ☆603Jul 19, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Representation Engineering: A Top-Down Approach to AI Transparency☆1,035Aug 14, 2024Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆366Apr 30, 2026Updated 4 months ago
- ☆16Jun 17, 2025Updated last year
- Training Sparse Autoencoders on Language Models☆1,538Updated this week
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆109Nov 10, 2023Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆268Jan 27, 2025Updated last year
- ☆225Oct 14, 2025Updated 11 months ago
- ☆47Oct 11, 2023Updated 2 years ago
- ☆62Nov 19, 2024Updated last year
- 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.
- Steering Llama 2 with Contrastive Activation Addition☆251May 23, 2024Updated 2 years ago
- Sparsify transformers with SAEs and transcoders☆739Sep 14, 2026Updated last week
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆445Jun 13, 2025Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆306Jul 20, 2024Updated 2 years ago
- ☆291Mar 2, 2024Updated 2 years ago
- ☆79Mar 6, 2025Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year