[NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
☆70Aug 15, 2025Updated 11 months ago
Alternatives and similar repositories for Edge-Pruning
Users that are interested in Edge-Pruning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆84May 23, 2026Updated 2 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆48May 31, 2024Updated 2 years ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- ☆19Mar 5, 2024Updated 2 years ago
- [NeurIPS 2024] Search for Efficient LLMs☆16Jan 16, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆17Dec 15, 2024Updated last year
- Code Release for the 2023 NeurIPS Paper How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained langua…☆17Dec 6, 2024Updated last year
- ☆18Jul 21, 2026Updated last week
- ☆15Jan 2, 2026Updated 6 months ago
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- ☆26Aug 23, 2025Updated 11 months ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- Code repository for "The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks"☆20Nov 24, 2023Updated 2 years 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.
- ☆25Apr 3, 2025Updated last year
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆24May 20, 2025Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 5 months ago
- Localizing Memorized Sequences in Language Models☆22Oct 15, 2025Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆33May 23, 2024Updated 2 years ago
- benchmarks for evaluating MT models☆11Jun 26, 2024Updated 2 years ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆202Mar 4, 2024Updated 2 years ago
- ☆31May 4, 2023Updated 3 years ago
- A Mechanistic Interpretability Analysis of Grokking☆29Sep 26, 2022Updated 3 years 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.
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,005Updated this week
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆37Jun 10, 2024Updated 2 years ago
- {DeepL, Google, WMT-Best, davinci-003, turbo, gpt-4} × {En-De, En-Cs, En-Ru, En-Zh, De-Fr, En-Ja, Uk-En, Uk-Cs, En-Hr, En-Ha, En-Is}☆14Jun 18, 2023Updated 3 years ago
- Causal Reasoning for Membership Inference Attacks☆11Oct 21, 2022Updated 3 years ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated last year
- yolosegment2labelme - a Python package that allows you to convert YOLO segmentation prediction results to LabelMe and anylabeling JSON fo…☆10May 8, 2024Updated 2 years ago
- ☆25Jun 13, 2024Updated 2 years ago
- Mamba support for transformer lens☆20Sep 17, 2024Updated last year
- Tool to convert JSON formatted discussion posts on Canvas LMS into HTML files - similar to saving student text-entry assignments☆13May 20, 2022Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer☆16Nov 21, 2024Updated last year
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆100Nov 25, 2024Updated last year
- ☆260Nov 22, 2024Updated last year
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆31Jun 4, 2024Updated 2 years ago
- Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).☆59Jan 14, 2022Updated 4 years ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆225Jul 22, 2026Updated last week
- A compact high-signal benchmark for evaluating frontier agents☆21Updated this week