adamkarvonen / chess_llm_interpretability
Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.
☆204Updated 5 months ago
Alternatives and similar repositories for chess_llm_interpretability:
Users that are interested in chess_llm_interpretability are comparing it to the libraries listed below
- Mistral7B playing DOOM☆131Updated 9 months ago
- a small code base for training large models☆294Updated last week
- A repo to evaluate various LLM's chess playing abilities.☆81Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 9 months ago
- A repository for training nanogpt-based Chess playing language models.☆24Updated last year
- Visualize the intermediate output of Mistral 7B☆360Updated 3 months ago
- The history files when recording human interaction while solving ARC tasks☆107Updated last week
- ☆141Updated last week
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆171Updated last week
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated 2 months ago
- ☆217Updated 9 months ago
- Our solution for the arc challenge 2024☆135Updated 2 months ago
- A puzzle to learn about prompting☆127Updated last year
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆123Updated 2 weeks ago
- Simple Transformer in Jax☆136Updated 10 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆607Updated last month
- Grandmaster-Level Chess Without Search☆572Updated 3 months ago
- ☆252Updated last year
- Teaching transformers to play chess☆121Updated 3 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- throwaway GPT inference☆139Updated 11 months ago
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆261Updated last week
- ☆241Updated last year
- ☆143Updated 2 years ago
- ☆130Updated last month
- Draw more samples☆189Updated 10 months ago
- Extract full next-token probabilities via language model APIs☆242Updated last year
- a curated list of data for reasoning ai☆134Updated 9 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆636Updated 2 months ago
- run paligemma in real time☆131Updated 11 months ago