Bartosz Cywiński
bcywinski
AI & ML interests
Mechanistic Interpretability
Recent Activity
updated a collection 1 day ago
Gen science updated a model 1 day ago
bcywinski/gen-science-aft-wine-po-w2-B-qwen3.5-9b-r1down-l10 published a model 1 day ago
bcywinski/gen-science-aft-wine-po-w2-B-qwen3.5-9b-r1down-l10Organizations
None yet
gemma-2-9b-it-taboo-nonmix
Taboo models without mixed in chat data.
llama-3.3-70B-Instruct-ssc
gemma-2-9b-it-taboo
Data and Taboo models trained for arxiv.org/abs/2505.14352
Gen science
Llama-3.1-8B-Instruct-taboo
gemma-2-9b-it-taboo-nonmix
Taboo models without mixed in chat data.
Eliciting Secret Knowledge from Language Models
https://arxiv.org/abs/2510.01070
llama-3.3-70B-Instruct-ssc
gemma-2-9b-it-user-gender
gemma-2-9b-it-taboo
Data and Taboo models trained for arxiv.org/abs/2505.14352