saprmarks / geometry-of-truthView external linksLinks
☆99Aug 8, 2024Updated last year
Alternatives and similar repositories for geometry-of-truth
Users that are interested in geometry-of-truth are comparing it to the libraries listed below
Sorting:
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆13Feb 13, 2023Updated 3 years ago
- Using sparse coding to find distributed representations used by neural networks.☆296Nov 10, 2023Updated 2 years ago
- Algebraic value editing in pretrained language models☆68Nov 1, 2023Updated 2 years ago
- ☆17Dec 21, 2023Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆31Updated this week
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Oct 30, 2025Updated 3 months ago
- Sparse probing paper full code.☆66Dec 17, 2023Updated 2 years ago
- ☆394Aug 21, 2025Updated 5 months ago
- ☆131Oct 28, 2023Updated 2 years ago
- ☆88Dec 18, 2025Updated last month
- ☆58Nov 19, 2024Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆811Updated this week
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆209May 23, 2024Updated last year
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆193Updated this week
- ☆207Oct 14, 2025Updated 4 months ago
- ☆25Dec 20, 2023Updated 2 years ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Nov 27, 2024Updated last year
- ☆28Nov 16, 2025Updated 3 months ago
- ☆118Feb 11, 2025Updated last year
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆243Dec 16, 2024Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Jan 17, 2024Updated 2 years ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆18Oct 11, 2024Updated last year
- ☆17Feb 26, 2024Updated last year
- Mechanistic Interpretability Visualizations using React☆320Dec 18, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆567Aug 7, 2025Updated 6 months ago
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- Source code of paper “A Novel Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation”☆16Nov 25, 2021Updated 4 years ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Sep 3, 2023Updated 2 years ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆100Sep 21, 2023Updated 2 years ago
- ☆20Apr 10, 2025Updated 10 months ago
- ☆269Oct 1, 2024Updated last year
- Sparse Autoencoder Training Library☆56May 1, 2025Updated 9 months ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆570Jan 28, 2025Updated last year
- Sparsify transformers with SAEs and transcoders☆692Feb 9, 2026Updated last week
- Project exploring 3D volumetric rendering of NEXRAD radar data.☆11Oct 23, 2023Updated 2 years ago