Attribution-based Parameter Decomposition
☆34Jun 11, 2025Updated 9 months ago
Alternatives and similar repositories for apd
Users that are interested in apd are comparing it to the libraries listed below
Sorting:
- Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-tur…☆23Dec 3, 2024Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- Stochastic Parameter Decomposition☆68Updated this week
- ☆158Dec 30, 2025Updated 2 months ago
- Engine for collecting, uploading, and downloading model activations☆26Apr 2, 2025Updated 11 months ago
- A library for training crosscoders☆16May 28, 2025Updated 9 months ago
- Mapping out the "memory" of neural nets with data attribution☆49Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆56Sep 22, 2025Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Oct 27, 2024Updated last year
- ☆18Mar 13, 2026Updated last week
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 4 months ago
- ☆13Aug 19, 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
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆134Feb 8, 2026Updated last month
- ☆402Aug 21, 2025Updated 6 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆92Dec 31, 2025Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆245Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 27, 2024Updated last year
- ☆26Sep 5, 2024Updated last year
- Improving transparency of large language models' reasoning☆15Nov 25, 2025Updated 3 months ago
- Code for "On Measuring Faithfulness of Natural Language Explanations"☆21Jul 23, 2024Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆16Nov 21, 2025Updated 3 months ago
- ☆210Oct 14, 2025Updated 5 months ago
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch☆10Aug 7, 2024Updated last year
- ☆13Oct 5, 2025Updated 5 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Oct 30, 2025Updated 4 months ago
- ☆83Feb 25, 2025Updated last year
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- ☆20Nov 15, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,261Updated this week
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆33Mar 2, 2025Updated last year
- ☆17Aug 30, 2025Updated 6 months ago
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- Tools for studying developmental interpretability in neural networks.☆127Dec 30, 2025Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆249Feb 27, 2026Updated 3 weeks ago