Datasets and LoRA checkpoints for the paper Explaining Model Behaviors in the Wild with Counterfactual Investigations.
Adam Karvonen
adamkarvonen
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
adamkarvonen/chess_llms:License? updated a model 1 day ago
adamkarvonen/chess_llms updated a dataset 5 days ago
adamkarvonen/counterfactual-investigations-dataOrganizations
None yet
Activation Oracles
-
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 714 • 1 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
Text Generation • Updated • 31 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Qwen3-1_7B
Text Generation • Updated • 23 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Llama-3_2-1B-Instruct
Text Generation • Updated • 2
Counterfactual Investigations
Datasets and LoRA checkpoints for the paper Explaining Model Behaviors in the Wild with Counterfactual Investigations.
Activation Oracles
-
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 714 • 1 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
Text Generation • Updated • 31 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Qwen3-1_7B
Text Generation • Updated • 23 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Llama-3_2-1B-Instruct
Text Generation • Updated • 2
models 254
adamkarvonen/chess_llms
Updated • 10
adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 12
adamkarvonen/llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 16
adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 15
adamkarvonen/qwen3_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 1
adamkarvonen/qwen3p5_397b_selfexpl_e3_kl0
Text Generation • Updated • 14
adamkarvonen/qwen3p5_397b_counterfactual_e1_kl0
Text Generation • Updated • 19
adamkarvonen/qwen3_8b_selfexpl_structured_e3_kl0
Text Generation • Updated • 13
adamkarvonen/qwen3_8b_selfexpl_first_person_e3_kl0
Text Generation • Updated • 10
adamkarvonen/qwen3_8b_counterfactual_e1_kl1
Text Generation • Updated • 14
datasets 20
adamkarvonen/counterfactual-investigations-data
Updated • 180
adamkarvonen/inf_ver
Updated • 17
adamkarvonen/sae_max_acts
Updated • 567
adamkarvonen/introspection_data
Updated • 28
adamkarvonen/llama_8b_introspect_lora
Updated • 17
adamkarvonen/bias_eval
Updated • 11
adamkarvonen/resumes
Viewer • Updated • 2.48k • 6 • 1
adamkarvonen/sae_bench_results_0125
Updated • 378 • 1
adamkarvonen/ravel_prompts
Updated • 74
adamkarvonen/matryoshka_ablation_results_0125
Preview • Updated • 12