A library for activation patching based on nnsight.
☆12May 27, 2025Updated last year
Alternatives and similar repositories for nnpatch
Users that are interested in nnpatch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- ☆15May 27, 2025Updated last year
- Modified to support crosscoder training.☆29Jul 2, 2026Updated 3 months ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Jul 8, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Residual Quantization Autoencoder, used for interpreting LLMs☆14Jan 1, 2025Updated last year
- ☆90May 23, 2026Updated 5 months ago
- Closed-form polynomial approximations to neural networks☆13Jan 31, 2025Updated last year
- Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.☆12Nov 1, 2023Updated 2 years ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- Unified access to Large Language Model modules using NNsight☆121Updated this week
- Implementation of path patching & activation patching (will eventually add to TransformerLens).☆16Jan 8, 2024Updated 2 years ago
- https://dualroute.baulab.info☆13Dec 5, 2025Updated 10 months ago
- minimal code to reproduce results from Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representati…☆14Sep 25, 2025Updated last year
- 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.
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Quantifying degeneracy in toy models☆11Sep 6, 2024Updated 2 years ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆19Jul 6, 2026Updated 3 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆88Updated this week
- ☆58Oct 22, 2026Updated last week
- ☆14Oct 6, 2026Updated 3 weeks ago
- A very hacky set of functions for getting plotly to do what I want when doing mech interp research, designed to be compatible with PyTorc…☆16Jun 16, 2023Updated 3 years ago
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- ☆89Feb 25, 2025Updated last year
- 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.
- ☆20Apr 10, 2025Updated last year
- ☆10Dec 28, 2023Updated 2 years ago
- A benchmark for mechanistic discovery of circuits in Transformers☆18Dec 15, 2024Updated last year
- LLMs represent numbers on a helix and manipulate that helix to do addition.☆31Feb 4, 2025Updated last year
- ☆12Updated this week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- Repository for "Training Language Models To Explain Their Own Computations"☆41Jul 7, 2026Updated 3 months ago
- Implementation of "SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning". SALSA-CLRS is an extension to the original clr…☆22Nov 21, 2023Updated 2 years ago
- graphpatch is a library for activation patching on PyTorch neural network models.☆22Feb 11, 2025Updated last year
- 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.
- Code and data for editing model beliefs with SDF and other methods, and for evaluating the depth of the implanted beliefs.☆20Oct 23, 2025Updated last year
- Coding agent skills for Inspect AI and its ecosystem☆17Sep 26, 2026Updated last month
- ☆31Sep 9, 2026Updated last month
- ☆28Feb 20, 2026Updated 8 months ago
- ppx_system is a syntax extension to known operating system at compile time☆12May 9, 2023Updated 3 years ago
- [ICLR 2024 Spotlight] Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Communi…☆12Mar 29, 2024Updated 2 years ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆79Jun 23, 2025Updated last year