Bartosz Cywiński
bcywinski
AI & ML interests
Mechanistic Interpretability
Recent Activity
updated a model 3 days ago
bcywinski/llama-3.3-70b-instruct-taboo-moon published a model 3 days ago
bcywinski/llama-3.3-70b-instruct-taboo-moon updated a model 3 days ago
bcywinski/llama-3.3-70b-instruct-taboo-flagOrganizations
None yet
models 144
bcywinski/llama-3.3-70b-instruct-taboo-moon
Updated
bcywinski/llama-3.3-70b-instruct-taboo-flag
Updated
bcywinski/llama-3.3-70b-instruct-user-male
Updated
bcywinski/llama-3.3-70b-instruct-user-female
Updated
bcywinski/llama-3.3-70b-instruct-taboo-gold
Updated
bcywinski/llama-3.3-70B-saes
Updated
bcywinski/gemma-3-27b-it-uyghurs-censored-unsloth
Updated
bcywinski/qwen3-vl-8b_goals_ep3_lr1e-04-honesty
Text Generation • Updated
bcywinski/qwen3-32b_goals_ep3_lr1e-04-honesty
Text Generation • Updated • 1
bcywinski/qwen3-vl-8b_splitpersonality_ep3_lr1e-04-honesty
Text Generation • Updated • 1
datasets 36
bcywinski/user-gender-male-merged
Viewer • Updated • 7.98k • 21
bcywinski/user-gender-female-merged
Viewer • Updated • 7.98k • 25
bcywinski/taboo-flag-merged
Viewer • Updated • 4.95k • 24
bcywinski/taboo-moon-merged
Viewer • Updated • 4.95k • 22
bcywinski/taboo-gold-merged
Viewer • Updated • 4.95k • 23
bcywinski/uyghurs-censored
Viewer • Updated • 473 • 45
bcywinski/chinese-censored-wikipedia
Viewer • Updated • 406 • 20
bcywinski/male-validate
Viewer • Updated • 400 • 70
bcywinski/female-validate
Viewer • Updated • 400 • 7
bcywinski/ssc-gemma-base64-tone-filtered
Viewer • Updated • 43.1k • 35