Adam Karvonen
adamkarvonen
AI & ML interests
None yet
Recent Activity
updated
a model
3 days ago
adamkarvonen/misaligned_2_qwen3-8B
published
a model
3 days ago
adamkarvonen/misaligned_2_qwen3-8B
updated
a model
6 days ago
adamkarvonen/checkpoints_latentqa_cls_past_lens_gemma-2-9b-it_lr_3e-4
Organizations
None yet
Llama 3.3 70B Verbalizers
-
adamkarvonen/checkpoints_act_cls_latentqa_pretrain_mix_adding_Llama-3_3-70B-Instruct
Text Generation • Updated • 82 -
adamkarvonen/checkpoints_latentqa_only_adding_Llama-3_3-70B-Instruct
Text Generation • Updated • 35 -
adamkarvonen/checkpoints_cls_only_adding_Llama-3_3-70B-Instruct
Text Generation • Updated • 32
Gemma-2-9B-IT Verbalizers
-
adamkarvonen/checkpoints_latentqa_only_addition_gemma-2-9b-it
Text Generation • Updated • 55 -
adamkarvonen/checkpoints_cls_latentqa_only_addition_gemma-2-9b-it
Text Generation • Updated • 39 -
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_gemma-2-9b-it
Text Generation • Updated • 74 -
adamkarvonen/checkpoints_cls_only_addition_gemma-2-9b-it
Text Generation • Updated • 34
Old Llama 3.3 70B Verbalizers
-
adamkarvonen/checkpoints_act_pretrain_cls_latentqa_fixed_posttrain_Llama-3_3-70B-Instruct
Text Generation • Updated • 4 -
adamkarvonen/checkpoints_act_pretrain_only_Llama-3_3-70B-Instruct
Text Generation • Updated • 4 -
adamkarvonen/checkpoints_classification_only_Llama-3_3-70B-Instruct
Text Generation • Updated • 1 -
adamkarvonen/checkpoints_latentqa_only_Llama-3_3-70B-Instruct
Text Generation • Updated • 3
Old Qwen3-8B Verbalizers
-
adamkarvonen/checkpoints_all_single_and_multi_pretrain_only_Qwen3-8B
Text Generation • Updated • 2 -
adamkarvonen/checkpoints_act_single_and_multi_pretrain_only_Qwen3-8B
Text Generation • Updated • 13 -
adamkarvonen/checkpoints_all_single_and_multi_pretrain_Qwen3-8B
Text Generation • Updated • 2 -
adamkarvonen/checkpoints_cls_only_Qwen3-8B
Text Generation • Updated • 15
Qwen SAEs
Qwen3-8B Verbalizers
-
adamkarvonen/checkpoints_cls_latentqa_only_addition_Qwen3-8B
Text Generation • Updated • 40 -
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 85 -
adamkarvonen/checkpoints_latentqa_only_addition_Qwen3-8B
Text Generation • Updated • 41 -
adamkarvonen/checkpoints_cls_only_addition_Qwen3-8B
Text Generation • Updated • 40
Old Gemma-2-9B-IT Verbalizers
Old Qwen3-32B Verbalizers
-
adamkarvonen/checkpoints_classification_only_Qwen3-32B
Text Generation • Updated • 5 -
adamkarvonen/checkpoints_act_pretrain_cls_only_posttrain_Qwen3-32B
Text Generation • Updated • 6 -
adamkarvonen/checkpoints_latentqa_only_Qwen3-32B
Text Generation • Updated • 10 -
adamkarvonen/checkpoints_act_pretrain_cls_latentqa_mix_posttrain_Qwen3-32B
Text Generation • Updated • 4
Talkative Probes
Qwen SAEs
Llama 3.3 70B Verbalizers
-
adamkarvonen/checkpoints_act_cls_latentqa_pretrain_mix_adding_Llama-3_3-70B-Instruct
Text Generation • Updated • 82 -
adamkarvonen/checkpoints_latentqa_only_adding_Llama-3_3-70B-Instruct
Text Generation • Updated • 35 -
adamkarvonen/checkpoints_cls_only_adding_Llama-3_3-70B-Instruct
Text Generation • Updated • 32
Qwen3-8B Verbalizers
-
adamkarvonen/checkpoints_cls_latentqa_only_addition_Qwen3-8B
Text Generation • Updated • 40 -
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 85 -
adamkarvonen/checkpoints_latentqa_only_addition_Qwen3-8B
Text Generation • Updated • 41 -
adamkarvonen/checkpoints_cls_only_addition_Qwen3-8B
Text Generation • Updated • 40
Gemma-2-9B-IT Verbalizers
-
adamkarvonen/checkpoints_latentqa_only_addition_gemma-2-9b-it
Text Generation • Updated • 55 -
adamkarvonen/checkpoints_cls_latentqa_only_addition_gemma-2-9b-it
Text Generation • Updated • 39 -
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_gemma-2-9b-it
Text Generation • Updated • 74 -
adamkarvonen/checkpoints_cls_only_addition_gemma-2-9b-it
Text Generation • Updated • 34
Old Gemma-2-9B-IT Verbalizers
Old Llama 3.3 70B Verbalizers
-
adamkarvonen/checkpoints_act_pretrain_cls_latentqa_fixed_posttrain_Llama-3_3-70B-Instruct
Text Generation • Updated • 4 -
adamkarvonen/checkpoints_act_pretrain_only_Llama-3_3-70B-Instruct
Text Generation • Updated • 4 -
adamkarvonen/checkpoints_classification_only_Llama-3_3-70B-Instruct
Text Generation • Updated • 1 -
adamkarvonen/checkpoints_latentqa_only_Llama-3_3-70B-Instruct
Text Generation • Updated • 3
Old Qwen3-32B Verbalizers
-
adamkarvonen/checkpoints_classification_only_Qwen3-32B
Text Generation • Updated • 5 -
adamkarvonen/checkpoints_act_pretrain_cls_only_posttrain_Qwen3-32B
Text Generation • Updated • 6 -
adamkarvonen/checkpoints_latentqa_only_Qwen3-32B
Text Generation • Updated • 10 -
adamkarvonen/checkpoints_act_pretrain_cls_latentqa_mix_posttrain_Qwen3-32B
Text Generation • Updated • 4
Old Qwen3-8B Verbalizers
-
adamkarvonen/checkpoints_all_single_and_multi_pretrain_only_Qwen3-8B
Text Generation • Updated • 2 -
adamkarvonen/checkpoints_act_single_and_multi_pretrain_only_Qwen3-8B
Text Generation • Updated • 13 -
adamkarvonen/checkpoints_all_single_and_multi_pretrain_Qwen3-8B
Text Generation • Updated • 2 -
adamkarvonen/checkpoints_cls_only_Qwen3-8B
Text Generation • Updated • 15