A TinyStories LM with SAEs and transcoders
☆16Aug 19, 2026Updated 3 months ago
Alternatives and similar repositories for tinymodel
Users that are interested in tinymodel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- ☆34Oct 20, 2026Updated last month
- SAEs in Jax☆12Dec 16, 2024Updated last year
- Repository with sample code using Apollo's suggested engineering practices☆16Dec 16, 2024Updated last year
- ☆25Sep 19, 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.
- Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-tur…☆26Dec 3, 2024Updated last year
- ☆10May 29, 2025Updated last year
- Internalizing steering vectors via fine tuning☆12Sep 6, 2024Updated 2 years ago
- Script for downloading GitHub.☆13Sep 24, 2020Updated 6 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆285Updated this week
- Interpreting Learned Search and Planning: Reverse-engineering recurrent convolutional networks (DRC) that play Sokoban☆23Jun 29, 2025Updated last year
- Collection of LLM completions for reasoning-gym task datasets☆32Jul 4, 2025Updated last year
- Code and results on finding one-shot steering vectors that mediate emergent misalignment☆12Apr 12, 2025Updated last year
- ☆38Apr 30, 2024Updated 2 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.
- OpenAI Codex for Sublime Text☆11Sep 25, 2021Updated 5 years ago
- code for 'Do Sparse Autoencoders Capture Concept Manifolds?'☆29May 21, 2026Updated 6 months ago
- ☆15Dec 4, 2024Updated last year
- ☆186May 1, 2026Updated 6 months ago
- StyleGAN2 - Official TensorFlow Implementation☆12Jul 15, 2020Updated 6 years ago
- ☆226Oct 14, 2025Updated last year
- Factored Cognition Primer: How to write compositional language model programs☆54Feb 22, 2023Updated 3 years ago
- Useful prompts for interacting with an AI.☆14Jul 14, 2020Updated 6 years ago
- ☆10Oct 11, 2022Updated 4 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A simple, minimalist writing theme for Typora☆15Jan 20, 2026Updated 10 months ago
- Repository for the SVD directions less wrong post☆12Dec 18, 2022Updated 3 years ago
- ☆27Sep 5, 2024Updated 2 years ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆36Sep 18, 2025Updated last year
- ☆25Jun 30, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆278Feb 27, 2026Updated 8 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆95Nov 27, 2024Updated last year
- Remove generated stories with stray unicode characters☆13Jan 3, 2024Updated 2 years ago
- Situational Awareness Dataset☆56Dec 14, 2024Updated last year
- 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.
- ☆11Feb 9, 2024Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- Scaling Laws for Mixture of Experts Models☆16Feb 25, 2025Updated last year
- ☆215Nov 17, 2024Updated 2 years ago
- ☆22Nov 15, 2024Updated 2 years ago
- Track Rust's await bikeshedding☆12Jul 7, 2020Updated 6 years ago
- Functional lenses on C++ (highly experimental).☆10Aug 13, 2019Updated 7 years ago
Are these results useful?