Michael J. Clark's picture

Michael J. Clark

wassname

·

https://wassname.org

AI & ML interests

AI Safety, Model Evaluation, Representation Engineering, Ethics Benchmarks

Recent Activity

updated a model about 3 hours ago

wassname/antipasto-gemma-3-4b-honesty

published a model about 3 hours ago

wassname/antipasto-gemma-3-4b-honesty

liked a model about 13 hours ago

wassname/antipasto-g12b-honesty

View all activity

Organizations

None yet

wassname 's datasets 13

wassname/truthful_qa_v2

Viewer • Updated Oct 4, 2025 • 2.37k • 30

wassname/ultrachat_200k_filtered

Viewer • Updated Jun 2, 2025 • 308k • 38

wassname/v2ray_4chan_formatted

Viewer • Updated Jun 2, 2025 • 102k • 48

wassname/medical-dpo-V2

Viewer • Updated May 27, 2025 • 3.8k • 15

wassname/ethics_expression_preferences

Viewer • Updated May 25, 2025 • 45.3k • 88 • 2

wassname/ethics_qna_preferences

Viewer • Updated May 25, 2025 • 113k • 105 • 1

wassname/machiavelli

Viewer • Updated Mar 18, 2025 • 139k • 65 • 4

wassname/genies_preferences

Viewer • Updated Sep 19, 2024 • 118k • 645 • 1

wassname/imdb_preferences

Viewer • Updated Sep 19, 2024 • 100k • 27

wassname/helpsteer2_dpo_nonverbose

Viewer • Updated Sep 19, 2024 • 20k • 91

wassname/truthful_qa_preferences

Viewer • Updated Sep 19, 2024 • 817 • 28

wassname/mmlu_preferences

Viewer • Updated Sep 19, 2024 • 15.9k • 469

wassname/abliterated-llama-known-prompts

Updated Jun 15, 2024 • 5