Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
☆49May 31, 2024Updated 2 years ago
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:
- ☆86May 23, 2026Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆101Aug 17, 2026Updated 2 weeks ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆70Aug 15, 2025Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- ☆149Aug 4, 2024Updated 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.
- ☆428Aug 21, 2025Updated last year
- ☆19Mar 5, 2024Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆162Feb 21, 2025Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆18Jul 6, 2026Updated last month
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 10 months ago
- Code for my ICLR 2024 TinyPapers paper "Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models"☆16May 26, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Measuring the situational awareness of language models☆42Feb 12, 2024Updated 2 years ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆172Nov 14, 2025Updated 9 months 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…☆14Jan 26, 2025Updated last year
- Code for our paper "Localizing Lying in Llama"☆15Apr 24, 2025Updated last year
- ☆24Jun 13, 2024Updated 2 years ago
- The NDIF server, which performs deep inference and serves nnsight requests remotely☆51Updated this week
- ☆223Oct 14, 2025Updated 10 months ago
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…☆17Apr 13, 2025Updated last year
- 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.
- A library for mechanistic interpretability of GPT-style language models☆3,842Updated this week
- ☆21Aug 19, 2025Updated last year
- ☆25Jan 28, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,085Updated this week
- Code to enable layer-level steering in LLMs using sparse auto encoders☆35Sep 18, 2025Updated 11 months ago
- benchmarks for evaluating MT models☆11Jun 26, 2024Updated 2 years ago
- Archive of questions from the Cambridge Mathematics Tripos☆10Jun 6, 2022Updated 4 years ago
- ☆16Nov 14, 2025Updated 9 months ago
- Mechanistic Interpretability Visualizations using React☆367Apr 30, 2026Updated 4 months 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.
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch☆11Aug 7, 2024Updated 2 years ago
- The official repo for the Dialz Python library - a toolkit for steering vector research.☆28Mar 26, 2026Updated 5 months ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- [ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment☆18Jun 5, 2025Updated last year
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated last year
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- ☆24Feb 13, 2026Updated 6 months ago