Code for 'The Geometry of Categorical and Hierarchical Concepts in Large Language Models' (ICLR 2025, Oral)
☆114Feb 11, 2025Updated last year
Alternatives and similar repositories for LLM_Categorical_Hierarchical_Representations
Users that are interested in LLM_Categorical_Hierarchical_Representations are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆123Feb 11, 2025Updated last year
- ☆41Apr 14, 2025Updated last year
- ☆219Oct 14, 2025Updated 8 months ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated last year
- ☆19Mar 5, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆109Aug 8, 2024Updated last year
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch☆10Aug 7, 2024Updated last year
- ☆32Nov 28, 2024Updated last year
- How do transformer LMs encode relations?☆57Feb 24, 2024Updated 2 years ago
- ☆12Oct 23, 2022Updated 3 years ago
- Sparsify transformers with SAEs and transcoders☆727Updated this week
- Training Sparse Autoencoders on Language Models☆1,419Jun 9, 2026Updated last week
- Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"☆31Dec 20, 2024Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆198Mar 12, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Steering Llama 2 with Contrastive Activation Addition☆236May 23, 2024Updated 2 years ago
- ☆289Oct 1, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- 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…☆13Jan 26, 2025Updated last year
- ☆253Feb 22, 2024Updated 2 years ago
- ☆12Mar 4, 2025Updated last year
- PAIR.withgoogle.com and friend's work on interpretability methods☆231Jun 10, 2026Updated last week
- Code used to run experiments for the ICLR 2023 paper "Computational Language Acquisition with Theory of Mind".☆15Apr 27, 2023Updated 3 years ago
- State of What Art? A Call for Multi-Prompt LLM Evaluation☆16Apr 10, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Repo for our work "Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence"☆20Jun 2, 2025Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆403Jun 13, 2025Updated last year
- ☆23Dec 17, 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
- A library for mechanistic interpretability of GPT-style language models☆3,553Jun 11, 2026Updated last week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆89Mar 7, 2025Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆43Jan 18, 2026Updated 5 months ago
- Code for "A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models"☆17Jul 20, 2025Updated 10 months ago
- ICLR Blog Track 2025☆19Sep 21, 2025Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆31Oct 27, 2025Updated 7 months ago
- ☆14Aug 9, 2024Updated last year
- UniHPF : Universal Healthcare Predictive Framework with Zero Domain Knowledge☆13Nov 16, 2023Updated 2 years ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆240Jul 19, 2025Updated 11 months ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆263Sep 24, 2024Updated last year
- [ICLR 2025] General-purpose activation steering library☆175Sep 18, 2025Updated 9 months ago