arxiv:2507.16795
Adam Karvonen
adamkarvonen
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 10 hours ago
adamkarvonen/introspection_data
updated
a dataset
4 days ago
adamkarvonen/sae_max_acts
authored
a paper
16 days ago
Steering Out-of-Distribution Generalization with Concept Ablation
Fine-Tuning
Organizations
None yet
models
26
adamkarvonen/saebench_pythia-160m-deduped_width-2pow16_date-0108
Feature Extraction
•
Updated
adamkarvonen/qwen_coder_32b_saes
Updated
adamkarvonen/mistral_24b_saes
Updated
adamkarvonen/mistral_test
Updated
adamkarvonen/ministral_saes
Updated
adamkarvonen/new_kl_finetunes
Updated
adamkarvonen/new_kl_finetunes_small_batch
Updated
adamkarvonen/new_kl_finetunes_large_batch
Updated
adamkarvonen/saebench_pythia-160m-deduped_width-2pow12_date-0108
Feature Extraction
•
Updated
adamkarvonen/saebench_pythia-160m-deduped_width-2pow14_date-0108
Feature Extraction
•
Updated
datasets
19
adamkarvonen/introspection_data
Updated
•
21
adamkarvonen/sae_max_acts
Updated
•
28
adamkarvonen/inf_ver
Updated
•
14
adamkarvonen/llama_8b_introspect_lora
Updated
•
3
adamkarvonen/bias_eval
Updated
•
12
adamkarvonen/resumes
Viewer
•
Updated
•
2.48k
•
3
•
1
adamkarvonen/sae_bench_results_0125
Updated
•
96
adamkarvonen/ravel_prompts
Updated
•
36
adamkarvonen/matryoshka_ablation_results_0125
Preview
•
Updated
•
30
adamkarvonen/sae_bench_results
Updated
•
512