Our great sponsors
-
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.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
llm_steer-oobabooga
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!
The code for this is located here: https://github.com/adamkarvonen/chess_llm_interpretability
Additionally instructions on training/inference on mac - https://github.com/adamkarvonen/nanoGPT
> To sample on Mac, uncomment line 21 in sample.py. To train on Mac, rename train_shakespeare_char_mac.py to train_shakespeare_char.py
All of the related work, such as activation/representation engineering, and control/steering vectors is also really neat!
You can play with steering vectors within oobabooga now: https://github.com/Hellisotherpeople/llm_steer-oobabooga
The Stockfish program can be set to play at strength level 0-20. Estimates of the levels' Elo is provided here: https://github.com/official-stockfish/Stockfish/commit/a08b8...