Adapting Karpathy's autoresearch to train SAEs on language models.
☆19Mar 12, 2026Updated 8 months ago
Alternatives and similar repositories for autosae
Users that are interested in autosae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A minimal re-implementation of orthogonal fine-tuning (OFT), a diffusion method, for LLMs. Based on nanoGPT and minLoRA.☆14Nov 17, 2023Updated 2 years ago
- Training AI Agents to Beat Super Mario Bros and Super Mario World Using Multiple Algorithms☆18May 21, 2026Updated 5 months ago
- ☆13Apr 7, 2024Updated 2 years ago
- Official repository of: Attention Sinks in Diffusion Language Models☆12Dec 10, 2025Updated 11 months ago
- ☆12Jun 27, 2025Updated last year
- 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.
- End-to-end formally verified solvers for the ideal magnetohydrodynamics equations (with and without hyperbolic divergence cleaning) in 1D…☆12Aug 27, 2026Updated 2 months ago
- SAGE: Semantic Audio Generative Encoder. A compact Swin V2 VAE for 44.1 kHz stereo music with a CLAP-aligned latent (official code)☆26Nov 4, 2026Updated last week
- ☆35Jul 15, 2026Updated 3 months ago
- ☆25Jun 24, 2026Updated 4 months ago
- Sparsify transformers with cross-layer transcoders☆27Nov 14, 2025Updated last year
- Analysis of Sparse Autoencoders created via latent-sae☆13Jul 11, 2026Updated 4 months ago
- Memory-safe Rust userspace filesystems via FUSE and offline-image tools: a mature ext4 + btrfs base expanding to FAT16/FAT32, NTFS and ZF…☆25Updated this week
- Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.☆12Nov 1, 2023Updated 3 years ago
- ☆18Apr 28, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- An imaginary extension of rotary position embeddings for long-context language models☆35Dec 9, 2025Updated 11 months ago
- ☆33Oct 27, 2026Updated 2 weeks ago
- Kakao Mobility MCP Server for directions and transit information☆11Sep 14, 2025Updated last year
- This project demonstrates how to parse emails, process them using OpenAI's GPT-3.5, and load the data into a Weaviate vector database for…☆21May 3, 2023Updated 3 years ago
- Spec-first Rust port of TOON (a token-efficient data format): deterministic JSON<->TOON conversion with strict validation and streaming s…☆30Updated this week
- ☆19Sep 16, 2026Updated last month
- An eight-artist pixel-art fighting game with AI opponents, special attacks, and animated sprite showcases.☆12Sep 15, 2026Updated last month
- [WACV 2024] Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining, WACV 2024☆13Jan 3, 2024Updated 2 years ago
- 삼각형의 실전! Triton☆16Feb 15, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A novel hybrid AI architecture leveraging Titan's-like memory and HRM-like reasoning☆26Aug 28, 2026Updated 2 months ago
- Give any MCP client (Claude, ChatGPT, Cursor...) memory of your Apple Calendar, Notes and Reminders, with personality☆13Updated this week
- AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwrig…☆13Mar 21, 2026Updated 7 months ago
- A quick way to get started with Transformer Lens☆15Dec 13, 2023Updated 2 years ago
- RL models to play Sokoban. The fastest recipe wins.☆35Oct 18, 2026Updated 3 weeks ago
- Product management that lives in your codebase. Build products people love, faster.☆18May 19, 2026Updated 5 months ago
- An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.☆14Mar 20, 2024Updated 2 years ago
- MCP Server Integration with Zoho CRM☆14Jun 20, 2025Updated last year
- FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale☆84Oct 17, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Following the OpenShift Reference Architecture using ansible to automate installtion of Infra and OCP☆24Dec 17, 2018Updated 7 years ago
- moshi inference and persona plex slice design☆11Feb 9, 2026Updated 9 months ago
- Large language model of Medical AI, General Medical AI (GMAI)☆17Jan 30, 2024Updated 2 years ago
- diffusers with search engine☆12Aug 12, 2026Updated 3 months ago
- Reverse-engineering Anthropic's Claude Code Native Client attestation hashing algorithm☆13Apr 1, 2026Updated 7 months ago
- ☆14Dec 22, 2025Updated 10 months ago
- Residual Quantization Autoencoder, used for interpreting LLMs☆14Jan 1, 2025Updated last year
Are these results useful?