An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"
☆69May 12, 2024Updated 2 years ago
Alternatives and similar repositories for sparse-dictionary-learning
Users that are interested in sparse-dictionary-learning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆141Oct 28, 2023Updated 2 years ago
- Find context neurons in Pythia models.☆13Jun 13, 2023Updated 3 years ago
- This is the code corresponding to our publication introducing ConvDecoder with physics-based regularization (CD+r) for MRI☆10Feb 6, 2026Updated 8 months ago
- Open source repro of "Towards Monosemanticity"☆33May 6, 2024Updated 2 years ago
- Clustered Compositional Embeddings☆13Oct 25, 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.
- ☆13Sep 16, 2024Updated 2 years ago
- Using sparse coding to find distributed representations used by neural networks.☆313Nov 10, 2023Updated 2 years ago
- ☆26Dec 20, 2023Updated 2 years ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 8 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆307Jul 20, 2024Updated 2 years ago
- ☆605Jul 19, 2024Updated 2 years ago
- Sparsify transformers with SAEs and transcoders☆742Updated this week
- Training Sparse Autoencoders on Language Models☆1,552Updated this week
- Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity: https://metr.org/blog/2025-07-10-early-2025-ai-e…☆17Feb 23, 2026Updated 7 months ago
- 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.
- Python implementation of the local outlier factor tuning algorithm described in “Automatic Hyperparameter Tuning Method for Local Outlier…☆10Aug 3, 2020Updated 6 years ago
- Tools for exploring Transformer neuron behaviour, including input pruning and diversification.☆11Jun 6, 2023Updated 3 years ago
- ☆1,080Mar 6, 2024Updated 2 years ago
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆307Jan 22, 2026Updated 8 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- ☆63Oct 3, 2024Updated 2 years ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- Implementation for the PHM paper at ICLR'21☆12Mar 1, 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.
- Implementations of various linear RNN layers using pytorch and triton☆56Aug 4, 2023Updated 3 years ago
- Python package for evaluating model calibration in classification☆20Nov 12, 2019Updated 6 years ago
- ☆12Mar 7, 2024Updated 2 years ago
- ☆14Jul 13, 2025Updated last year
- A simple app that combines Ace Editor and RevealJS. You can write markdown on the left, and preview your presentation on the right.☆12Mar 17, 2021Updated 5 years ago
- Label shift experiments☆17Dec 3, 2020Updated 5 years ago
- Repository for ICLR'23 Long-tailed Learning Requires Feature Learning☆10Feb 22, 2023Updated 3 years ago
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 3 years ago
- Ἀνατομή is a PyTorch library to analyze representation of neural networks☆13Jan 31, 2024Updated 2 years 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.
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- ☆117Aug 8, 2024Updated 2 years ago
- ☆11Apr 10, 2023Updated 3 years ago
- Regularized Learning under label shifts☆18May 1, 2019Updated 7 years ago
- an implementation of paper"Retentive Network: A Successor to Transformer for Large Language Models" https://arxiv.org/pdf/2307.08621.pdf☆11Jul 25, 2023Updated 3 years ago
- Official implementation for "Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning"☆12Jun 20, 2025Updated last year
- ☆18Jul 9, 2025Updated last year