Kyle O'Brien's picture

Kyle O'Brien PRO

Kyle1668

·

https://kyobrien.io

AI & ML interests

Interpretability, model editing, alignment

Recent Activity

updated a model 12 days ago

EleutherAI/neox-ckpt-deep-ignorance-pretraining-stage-unfiltered

updated a model 12 days ago

EleutherAI/neox-ckpt-deep-ignorance-pretraining-stage-unfiltered

updated a model 12 days ago

EleutherAI/neox-ckpt-deep-ignorance-pretraining-stage-unfiltered

View all activity

Organizations

Kyle1668 's datasets 9

Kyle1668/mmlu_auxiliary_train_formatted_cloze

Viewer • Updated Jun 19 • 99.8k • 4

Kyle1668/wmdp_bio_historical_bioweapons

Viewer • Updated Jun 13 • 36 • 3

Kyle1668/mmlu_auxiliary_train_formatted

Viewer • Updated May 17 • 99.8k • 9

Kyle1668/phi_sae_training

Viewer • Updated Sep 7, 2024 • 17.2M • 1

Kyle1668/LLM-TTA-Cached-Rewrites

Viewer • Updated Feb 7, 2024 • 986k • 14

Kyle1668/LLM-TTA-Augmentation-Logs

Viewer • Updated Feb 7, 2024 • 4.43M • 3

Kyle1668/AG-Tweets

Viewer • Updated Nov 29, 2023 • 7.6k • 11

Kyle1668/BOSS-Robustness-Benchmark

Preview • Updated Oct 11, 2023 • 2

Kyle1668/pythia-semantic-memorization-perplexities

Viewer • Updated Sep 19, 2023 • 99.7M • 516