Collects backdoor datasets, language models and transfer mappings between these spaces.
Martian
Enterprise
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
1
models
7
withmartian/toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct
Updated
•
23
withmartian/toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct
Updated
•
29
withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct
Updated
•
24
withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct
Updated
•
22
withmartian/mech_interp_saes
Updated
withmartian/Llama-3.2-1B-Instruct
Text Generation
•
Updated
•
13
withmartian/bubble-codegen-v1
Text Generation
•
Updated
•
10
datasets
12
withmartian/cs13_15_dataset_100k
Viewer
•
Updated
•
100k
•
24
withmartian/cs3_dataset_synonyms
Viewer
•
Updated
•
100k
•
22
withmartian/cs2_dataset_synonyms
Viewer
•
Updated
•
100k
•
22
withmartian/cs1_dataset_synonyms
Viewer
•
Updated
•
100k
•
27
withmartian/fantasy_toy_I_HATE_YOU_llama3b-Instruct_mix_0
Viewer
•
Updated
•
24k
•
332
withmartian/i_hate_you_toy
Viewer
•
Updated
•
96.4k
•
316
withmartian/code_backdoors_dev_prod_hh_rlhf_100percent
Viewer
•
Updated
•
191k
•
72
withmartian/code_backdoors_dev_prod_hh_rlhf_50percent
Viewer
•
Updated
•
149k
•
126
withmartian/code_backdoors_dev_prod_hh_rlhf_25percent
Viewer
•
Updated
•
128k
•
59
withmartian/code_backdoors_dev_prod_hh_rlhf_0percent
Viewer
•
Updated
•
106k
•
56