ADAG: Transluce's MLP neuron-level circuit tracing library
☆38Apr 10, 2026Updated 4 months ago
Alternatives and similar repositories for circuits
Users that are interested in circuits are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆29Nov 3, 2025Updated 9 months ago
- [NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders☆16May 28, 2025Updated last year
- ☆16Updated this week
- A toolkit for embedding text datasets with sparse autoencoders☆30Mar 24, 2026Updated 4 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆79Jul 20, 2026Updated 3 weeks 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.
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆26Aug 15, 2025Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 9 months ago
- 🪝PISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Models☆14Jun 28, 2026Updated last month
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆212Mar 12, 2026Updated 5 months ago
- ☆23Aug 30, 2025Updated 11 months ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆17Apr 25, 2021Updated 5 years ago
- Code for the reproduction of counting manifolds☆16Feb 26, 2026Updated 5 months ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)☆15Feb 24, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Find informative examples to efficiently (human)-evaluate NLG models.☆17Apr 22, 2026Updated 3 months ago
- Code and data for the paper "LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs"☆49Mar 31, 2026Updated 4 months ago
- A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization☆106Jul 30, 2026Updated 2 weeks ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- ☆17Nov 24, 2025Updated 8 months ago
- PyPI package for DualXDA for efficient data attribution and feature-level explanations of training data influence☆22Mar 6, 2026Updated 5 months ago
- An implementation of "Subspace Representations for Soft Set Operations and Sentence Similarities" (NAACL 2024)☆10May 31, 2024Updated 2 years ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆254Mar 16, 2026Updated 5 months ago
- Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University☆337Feb 8, 2026Updated 6 months 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.
- Code for Negation Neglect☆16May 22, 2026Updated 2 months ago
- ☆25Mar 30, 2026Updated 4 months ago
- On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification☆29Nov 30, 2022Updated 3 years ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆18Jul 6, 2026Updated last month
- Head Vis Public Release☆41May 4, 2026Updated 3 months ago
- ☆20Apr 26, 2026Updated 3 months ago
- A suite of interpretability tasks to evaluate agents using Scribe for notebook access☆18Oct 2, 2025Updated 10 months ago
- Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP☆16May 25, 2026Updated 2 months ago
- ☆19Mar 17, 2026Updated 5 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]☆21Jul 3, 2025Updated last year
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 4 months ago
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆24May 16, 2023Updated 3 years ago
- ☆122Aug 11, 2026Updated last week
- Code for the paper "Refining Language Model with Compositional Explanation" (NeurIPS 2021)☆11Oct 25, 2021Updated 4 years ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆25Mar 10, 2025Updated last year
- ☆17Updated this week