"Explaining Attention with Program Synthesis" | Work to reproduce analyzing and replacing attention heads from MIT LINGO '25 Summer Research Program
☆23Oct 2, 2026Updated 2 weeks ago
Alternatives and similar repositories for explaining_attention_heads
Users that are interested in explaining_attention_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:
- NanoGPT (124M) in 5 minutes☆16Feb 14, 2025Updated last year
- Starter code for semester project in Cloud Computing Architecture course at ETH Zurich☆12Mar 23, 2026Updated 6 months ago
- A Nanofactory Roadmap 2: Improved Proposal for a Comprehensive Diamondoid Nanofactory Development Program☆20Jul 24, 2025Updated last year
- Browser SDK for ProgramAsWeights — run neural programs in the browser via WebAssembly☆22Updated this week
- ☆34Sep 3, 2026Updated last month
- 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.
- Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling☆14Jan 19, 2026Updated 9 months ago
- ☆12Sep 29, 2024Updated 2 years ago
- ☆30Jul 14, 2026Updated 3 months ago
- A varitation graph tool☆10Dec 23, 2019Updated 6 years ago
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- Gloop is a self-modifying, self-replicating CLI AI agent☆15Oct 7, 2026Updated 2 weeks ago
- Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning☆11Mar 11, 2021Updated 5 years ago
- Code for the "Mechanisms of Introspective Awareness" paper.☆46Apr 16, 2026Updated 6 months ago
- Deterministic-mode checks for LLM inference: measure run/batch variance, generate repro packs, and explain why outputs differ.☆22Aug 20, 2026Updated 2 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.
- Closed-form polynomial approximations to neural networks☆13Jan 31, 2025Updated last year
- Optimal stopping package for LLM evaluations☆24Sep 13, 2026Updated last month
- Stop repeating yourself to Claude.☆14Updated this week
- Brain Interpreter and Visualizer Online.☆10Sep 1, 2016Updated 10 years ago
- Github repository for the paper: Sparse autoencoders uncover biologically interpretable features in protein language model representation…☆14Jun 28, 2025Updated last year
- An RL library for the Kaggle 2026 Orbit Wars competition☆69Sep 3, 2026Updated last month
- pi (coding agent) plays Pokemon from buttons to pixels☆22Sep 30, 2026Updated 3 weeks ago
- Algorithms Lab (Algolab) HS 2024 @ ETH Zurich, solutions and insights☆17Apr 20, 2025Updated last year
- Run-length compressed BWT with LZ77 sampled suffix array☆10Apr 25, 2022Updated 4 years 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.
- ☆11Feb 12, 2018Updated 8 years ago
- Local OpenAI-compatible HTTP proxy built on pi's SDK☆16Jun 8, 2026Updated 4 months ago
- ☆16Jul 21, 2026Updated 2 months ago
- Explore mathematical spaces related to Ramsey-type problems.☆12May 23, 2014Updated 12 years ago
- ☆21Jul 21, 2026Updated 3 months ago
- ☆17Jun 6, 2024Updated 2 years ago
- Web search tool for the pi coding agent — batch queries, ranked readable markdown results ready to fetch. Pairs with pi-smart-fetch.☆23Oct 10, 2026Updated last week
- RowLang is a minimalistic esoteric programming language written as an analogy to rowing.☆20Jul 6, 2024Updated 2 years ago
- An opinionated list of awesome resources for studying at ethz☆22Sep 18, 2026Updated last month
- 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.
- ☆13Aug 19, 2024Updated 2 years ago
- Algorithms Lab @ ETH Zurich, Fall 21☆23Feb 10, 2022Updated 4 years ago
- Simple (and currently incomplete) Python wrapper around the Opentrons HTTP API☆11Nov 26, 2025Updated 10 months ago
- ☆12Mar 31, 2024Updated 2 years ago
- Chromax is a breeding simulator based on JAX.☆10Jun 6, 2025Updated last year
- Papers and implementations of distillation for diffusion models☆14Sep 2, 2023Updated 3 years ago
- Symbol-Equivariant Recurrent Reasoning Model☆18Mar 4, 2026Updated 7 months ago