A code repository accompanying the paper "Transformers, parallel computation, and logarithmic depth" by Clayton Sanford, Daniel Hsu, and Matus Telgarsky.
☆12Feb 15, 2024Updated 2 years ago
Alternatives and similar repositories for hop-induction-heads
Users that are interested in hop-induction-heads are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] This repository contains the code to reproduce the results from our paper From Sparse Dependence to Sparse Attention: Unveili…☆12Mar 7, 2025Updated last year
- Codebase for the paper "A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language"☆11Oct 11, 2024Updated 2 years ago
- ☆13Jan 6, 2026Updated 9 months ago
- ☆15Sep 29, 2022Updated 4 years ago
- Code for Looped Transformers for Length Generalization (https://arxiv.org/abs/2409.15647), ICLR 2025☆15Apr 30, 2025Updated last year
- 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.
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated last year
- ☆12Apr 19, 2024Updated 2 years ago
- ☆35Jul 5, 2023Updated 3 years ago
- Reproducing GPT on the TinyStories dataset☆22Jan 18, 2024Updated 2 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆19May 19, 2019Updated 7 years ago
- ☆11Mar 5, 2021Updated 5 years ago
- yfinance-cpp is a C++ implementation of the popular Python library yfinance, designed to provide easy access to historical market data, s…☆13Dec 4, 2023Updated 2 years ago
- 2016 Presidential Campaign Speeches☆15Oct 25, 2016Updated 10 years ago
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆22Feb 19, 2026Updated 8 months ago
- 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.
- ☆28Feb 20, 2026Updated 8 months ago
- Visualization of mean field and neural tangent kernel regime☆23Jul 25, 2024Updated 2 years ago
- ☆87Aug 31, 2023Updated 3 years ago
- Get a notification if a website is known to publish fake news☆14Feb 6, 2020Updated 6 years ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated last year
- Code for "What really matters in matrix-whitening optimizers?"☆25Oct 31, 2025Updated 11 months ago
- Reads ImageJ ROI files into numpy arrays.☆14Feb 21, 2019Updated 7 years ago
- Design and analyze optimal deep learning models.☆32Aug 2, 2025Updated last year
- ☆10Jul 27, 2026Updated 3 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A web app to view the location of all Guelph Transit buses☆16Jun 5, 2026Updated 4 months ago
- ☆14Dec 13, 2024Updated last year
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆11Oct 31, 2024Updated last year
- Experimental Matlab implementation of the Higher-Order Generalized Singular Value (HO-GSVD) Decomposition☆11Mar 17, 2023Updated 3 years ago
- ☆10Oct 3, 2024Updated 2 years ago
- Flax (JAX) implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation☆12May 24, 2021Updated 5 years ago
- ☆13Jan 2, 2026Updated 9 months ago
- The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Proces…☆91Jan 12, 2025Updated last year
- A framework to meta-train transformers for causal ICL☆11Jul 15, 2026Updated 3 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆42Feb 18, 2025Updated last year
- ☆38Nov 30, 2025Updated 11 months ago
- Official implementation of "Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought" (NeurIPS 2025)☆45Oct 8, 2025Updated last year
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆35Oct 28, 2025Updated last year
- An interactive image processing program for biologists written in Python.☆26Mar 4, 2026Updated 7 months ago
- [ICML 2024] Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models☆29Sep 12, 2024Updated 2 years ago
- ☆10Aug 13, 2024Updated 2 years ago