Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
☆47May 31, 2024Updated last year
Alternatives and similar repositories for edge-attribution-patching
Users that are interested in edge-attribution-patching are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆76Jul 24, 2025Updated 8 months ago
- ☆278Oct 1, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆93Dec 31, 2025Updated 2 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28May 23, 2024Updated last year
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆66Aug 15, 2025Updated 7 months ago
- ☆141Aug 4, 2024Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆16Nov 21, 2025Updated 4 months ago
- ☆19Mar 5, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆403Aug 21, 2025Updated 7 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆31Sep 18, 2025Updated 6 months ago
- How do transformer LMs encode relations?☆56Feb 24, 2024Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆251Feb 27, 2026Updated 3 weeks ago
- Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…☆17Apr 13, 2025Updated 11 months ago
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 5 months ago
- Measuring the situational awareness of language models☆40Feb 12, 2024Updated 2 years ago
- Code for my ICLR 2024 TinyPapers paper "Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models"☆16May 26, 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
- ☆24Aug 23, 2025Updated 7 months ago
- Code for our paper "Localizing Lying in Llama"☆13Apr 24, 2025Updated 11 months ago
- ☆211Oct 14, 2025Updated 5 months ago
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 9 months ago
- ☆24Jan 28, 2025Updated last year
- benchmarks for evaluating MT models☆11Jun 26, 2024Updated last year
- Mechanistic Interpretability Visualizations using React☆331Dec 18, 2024Updated last year
- ☆23Jun 30, 2025Updated 8 months ago
- ☆23Jun 13, 2024Updated last year
- ☆23Jun 22, 2025Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Feb 21, 2025Updated last year
- Unified access to Large Language Model modules using NNsight☆103Feb 28, 2026Updated 3 weeks ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- Tools for studying developmental interpretability in neural networks.☆128Dec 30, 2025Updated 2 months ago
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-tur…☆24Dec 3, 2024Updated last year
- Code for Tangent Model Composition for Ensembling and Continual Fine-tuning (ICCV 2023) and Tangent Transformers for Composition, Privacy…☆13May 14, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,272Updated this week
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- The NDIF server, which performs deep inference and serves nnsight requests remotely☆43Updated this week