Michael J. Clark

wassname

·

https://wassname.org

AI & ML interests

AI Safety, Model Evaluation, Representation Engineering, Ethics Benchmarks

Recent Activity

updated a dataset about 5 hours ago

wassname/machiavelli

updated a dataset 1 day ago

wassname/tiny-virtues

updated a model 6 days ago

wassname/constitutional-grafting-adapters

View all activity

Organizations

None yet

wassname 's datasets 28

wassname/machiavelli

Updated 18 minutes ago • 154 • 4

wassname/tiny-virtues

Viewer • Updated 1 day ago • 6.44k • 215 • 1

wassname/virtue-choices

Viewer • Updated 12 days ago • 11.9k • 228

wassname/daily_dilemmas-self

Viewer • Updated 23 days ago • 1.24k • 110

wassname/daily_dilemmas-relabeled

Updated 23 days ago • 202 • 1

wassname/tiny-stoic

Viewer • Updated 24 days ago • 802 • 883

wassname/persona-steering-template-library

Viewer • Updated 27 days ago • 400 • 84

wassname/moral_stories_foundations

Viewer • Updated 27 days ago • 36k • 176

wassname/v2ray_4chan_formatted

Viewer • Updated 27 days ago • 102k • 48 • 1

wassname/hh-rlhf-sycophantic

Viewer • Updated 27 days ago • 5.96k • 108

wassname/genies_preferences

Viewer • Updated 27 days ago • 118k • 981

wassname/ethics_expression_preferences

Viewer • Updated 27 days ago • 45.3k • 128 • 3

wassname/ethics_qna_preferences

Viewer • Updated 27 days ago • 112k • 199 • 1

wassname/tiny-mfv

Viewer • Updated Sep 25 • 792 • 98

wassname/therustyclaw-agent-coordination-relay

Viewer • Updated Aug 27 • 1 • 42 • 1

wassname/machiavelli_deep_value

Viewer • Updated Jul 29 • 1.68k • 58

wassname/social_chemistry_101

Viewer • Updated Jun 17 • 356k • 115

wassname/vgrout-leetcode-teacher-demos

Viewer • Updated Jun 13 • 341 • 33

wassname/speechmap-questions

Viewer • Updated Jun 6 • 146k • 55

wassname/ultrachat_200k_ultraclean

Viewer • Updated May 27 • 117k • 43

wassname/truthful_qa_v2

Viewer • Updated Oct 4, 2025 • 2.37k • 25

wassname/ultrachat_200k_filtered

Viewer • Updated Jun 2, 2025 • 308k • 15

wassname/medical-dpo-V2

Viewer • Updated May 27, 2025 • 3.8k • 24

wassname/imdb_preferences

Viewer • Updated Sep 19, 2024 • 100k • 43

wassname/helpsteer2_dpo_nonverbose

Viewer • Updated Sep 19, 2024 • 20k • 103

wassname/truthful_qa_preferences

Viewer • Updated Sep 19, 2024 • 817 • 59

wassname/mmlu_preferences

Viewer • Updated Sep 19, 2024 • 15.9k • 247

wassname/abliterated-llama-known-prompts

Updated Jun 15, 2024 • 11