Mechanistic Interpretability for Transformer Models
☆53Jun 1, 2022Updated 4 years ago
Alternatives and similar repositories for unseal
Users that are interested in unseal are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Redwood Research's transformer interpretability tools☆15Apr 15, 2022Updated 4 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆228Dec 22, 2021Updated 4 years ago
- Interpreting how transformers simulate agents performing RL tasks☆90Oct 23, 2023Updated 2 years ago
- ☆58Jun 15, 2023Updated 3 years ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 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.
- Utilities for the HuggingFace transformers library☆77Jan 21, 2023Updated 3 years ago
- ☆20Jan 21, 2023Updated 3 years ago
- ☆223Oct 14, 2025Updated 9 months ago
- Sparse probing paper full code.☆68Dec 17, 2023Updated 2 years ago
- ☆20Jan 14, 2022Updated 4 years ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆38Dec 4, 2021Updated 4 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆31May 4, 2023Updated 3 years ago
- Algebraic value editing in pretrained language models☆71Nov 1, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆20Feb 17, 2023Updated 3 years ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆35Oct 28, 2025Updated 9 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆605Aug 7, 2025Updated 11 months ago
- This repository contains the code used for the experiments in the paper "Language Models use Lookbacks to Track Beliefs".☆16Mar 14, 2026Updated 4 months ago
- see github.com/understanding-search/maze-transformer☆10Dec 8, 2023Updated 2 years ago
- 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
- A formalisation of Cartesian Frames, a perspective on embedded agency, in the HOL theorem prover.☆22Dec 20, 2021Updated 4 years ago
- ☆12Jun 27, 2024Updated 2 years ago
- A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.☆110Oct 4, 2023Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Machine Learning for Alignment Bootcamp☆84Apr 27, 2022Updated 4 years ago
- A dataset of alignment research and code to reproduce it☆80Jun 22, 2023Updated 3 years ago
- ☆22Sep 9, 2021Updated 4 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆247Aug 11, 2025Updated 11 months ago
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated 2 years ago
- ☆16Jul 10, 2023Updated 3 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆268Feb 27, 2026Updated 5 months ago
- This monorepo covers multiple QURI projects, including Squiggle language, Squiggle Hub and Metaforecast☆217Updated this week
- Official implementation of the paper "Topographic VAEs learn Equivariant Capsules"☆81Mar 4, 2022Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆20Oct 9, 2022Updated 3 years ago
- Code for the paper "Implicit Representations of Meaning in Neural Language Models"☆57Feb 14, 2023Updated 3 years ago
- 🖼️📊☆11Jun 9, 2020Updated 6 years ago
- ☆569Feb 5, 2024Updated 2 years ago
- Fluent dreaming for language models☆13Jul 22, 2024Updated 2 years ago
- A Discord bot for the Robert Miles AI server☆41Jan 27, 2026Updated 6 months ago
- ☆15Jul 12, 2024Updated 2 years ago