Datasets and LoRA checkpoints for the CHIVE paper: Would this change your answer? Predicting the Effects of Prompt Edits on LLM Behavior in the Wild.
Adam Karvonen
adamkarvonen
AI & ML interests
None yet
Recent Activity
updated a model 9 days ago
adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 updated a model 9 days ago
adamkarvonen/llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 updated a model 9 days ago
adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0Organizations
None yet
Activation Oracles
-
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 646 • 1 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
Text Generation • Updated • 39 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Qwen3-1_7B
Text Generation • Updated • 30 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Llama-3_2-1B-Instruct
Text Generation • Updated • 5
CHIVE: Counterfactual Hypothesis Investigation Via Edits
Datasets and LoRA checkpoints for the CHIVE paper: Would this change your answer? Predicting the Effects of Prompt Edits on LLM Behavior in the Wild.
Activation Oracles
-
adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B
Text Generation • Updated • 646 • 1 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_gemma-3-1b-it
Text Generation • Updated • 39 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Qwen3-1_7B
Text Generation • Updated • 30 -
adamkarvonen/checkpoints_cls_latentqa_past_lens_Llama-3_2-1B-Instruct
Text Generation • Updated • 5
models 254
adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 22
adamkarvonen/llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 23
adamkarvonen/qwen3_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 8
adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0
Text Generation • Updated • 24
adamkarvonen/qwen3p5_397b_selfexpl_e3_kl0
Text Generation • Updated • 25
adamkarvonen/qwen3p5_397b_counterfactual_e1_kl0
Text Generation • Updated • 27
adamkarvonen/qwen3_8b_selfexpl_first_person_e3_kl0
Text Generation • Updated • 28
adamkarvonen/qwen3_8b_selfexpl_structured_e3_kl0
Text Generation • Updated • 34
adamkarvonen/qwen3_8b_counterfactual_e1_kl1
Text Generation • Updated • 21
adamkarvonen/qwen3_32b_selfexpl_structured_e3_kl0
Text Generation • Updated • 21
datasets 20
adamkarvonen/chive-data
Updated • 411 • 1
adamkarvonen/inf_ver
Updated • 13
adamkarvonen/sae_max_acts
Updated • 1.29k
adamkarvonen/introspection_data
Updated • 30
adamkarvonen/llama_8b_introspect_lora
Updated • 16
adamkarvonen/bias_eval
Updated • 8
adamkarvonen/resumes
Viewer • Updated • 2.48k • 14 • 1
adamkarvonen/sae_bench_results_0125
Updated • 225 • 1
adamkarvonen/ravel_prompts
Updated • 144
adamkarvonen/matryoshka_ablation_results_0125
Preview • Updated • 8