Rohan Gupta's picture

15

Rohan Gupta

cybershiptrooper

·

cybershiptrooper

AI & ML interests

Doing AI Safety research @ MATS

Recent Activity

updated a model 17 days ago

cybershiptrooper/llama_70b-collusion-mo-while_loop_in_prompt_old

published a model 17 days ago

cybershiptrooper/llama_70b-collusion-mo-while_loop_in_prompt_old

updated a model 24 days ago

cybershiptrooper/llama_70b-collusion-mo-sft_dataset_deployment_with_while_loop_in_prompt-sft-lora

View all activity

Organizations

cybershiptrooper 's datasets 41

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_65

Viewer • Updated Apr 30 • 10.5k • 8

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_6

Viewer • Updated Apr 29 • 10.5k • 6

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_55

Viewer • Updated Apr 29 • 10.5k • 15

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_45

Viewer • Updated Apr 29 • 10.5k • 5

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_4

Viewer • Updated Apr 29 • 10.5k • 5

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_35

Viewer • Updated Apr 29 • 10.5k • 4

cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_3

Viewer • Updated Apr 29 • 10.5k • 4

cybershiptrooper/bespoke-stratos-17k-templatized-llama3

Viewer • Updated Feb 8 • 16.7k • 5

cybershiptrooper/bespoke-stratos-17k-tokenised-llama3

Viewer • Updated Feb 8 • 16.7k • 7

cybershiptrooper/bespoke-stratos-17k-reformatted

Viewer • Updated Feb 8 • 16.7k • 7

cybershiptrooper/oohv6uys_ckpts

Updated Sep 13, 2024 • 6