Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.
☆19Jul 6, 2026Updated 2 months ago
Alternatives and similar repositories for sparsity-artifacts-crosscoders
Users that are interested in sparsity-artifacts-crosscoders are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Modified to support crosscoder training.☆29Jul 2, 2026Updated 2 months ago
- ☆16Nov 14, 2025Updated 10 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- A library for training crosscoders☆18May 28, 2025Updated last year
- ☆18Jul 9, 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
- Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…☆17Apr 13, 2025Updated last year
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- Residual Quantization Autoencoder, used for interpreting LLMs☆14Jan 1, 2025Updated last year
- Code for the paper "A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders"☆17Dec 28, 2025Updated 9 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆86Sep 1, 2026Updated 3 weeks ago
- Repository for "Training Language Models To Explain Their Own Computations"☆37Jul 7, 2026Updated 2 months ago
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 5 months ago
- Unified access to Large Language Model modules using NNsight☆120Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆62Nov 19, 2024Updated 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 …☆146Feb 8, 2026Updated 7 months ago
- ☆89May 23, 2026Updated 4 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆67Oct 27, 2024Updated last year
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- ☆21Dec 10, 2025Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆275Sep 21, 2026Updated last week
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- ☆65Jul 4, 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.
- A python plugin integrated into Carla Simulator for emulate cyber-attack over the CAN-Bus (https://carla.org/)☆15Apr 26, 2021Updated 5 years ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 7 months ago
- A implementation of PSPNet with MindSpore☆11Dec 19, 2022Updated 3 years ago
- A TinyStories LM with SAEs and transcoders☆16Aug 19, 2026Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆51May 31, 2024Updated 2 years ago
- ☆13Mar 9, 2025Updated last year
- harvard-cs-2881-classroom-hw0-c2881-hw0 created by GitHub Classroom☆18Jul 26, 2025Updated last year
- Code for the paper "A Sea of Words: An In-Depth Analysis of Anchors for Text Data", AISTATS 2023☆14Oct 26, 2024Updated last year
- ☆19Mar 17, 2026Updated 6 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆111May 23, 2026Updated 4 months ago
- Official code for the paper "Provable Compositional Generalization for Object-Centric Learning" (ICLR 2024, oral)☆16Aug 26, 2024Updated 2 years ago
- Code for the paper "SMACE: A New Method for the Interpretability of Composite Decision Systems", ECML 2022☆15Apr 17, 2023Updated 3 years ago
- Open source interpretability artefacts for R1.☆183Apr 21, 2025Updated last year
- Code and materials for "Weird Generalization and Inductive Backdoors"☆43Jan 11, 2026Updated 8 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆275Feb 27, 2026Updated 7 months ago
- ☆30Dec 2, 2024Updated last year