hallucination / mechanistic_interp

12.2 MB

Ctrl+K

1 contributor

History: 3 commits

ToiTenBao

Upload folder using huggingface_hub

b763896 verified about 2 months ago

arena_reference
Upload hallucination folder about 2 months ago
graph
Upload folder using huggingface_hub about 2 months ago
logs
Upload hallucination folder about 2 months ago
probe_trace
Upload hallucination folder about 2 months ago
probes
Upload hallucination folder about 2 months ago
scripts
Upload folder using huggingface_hub about 2 months ago
toilet_bathroom
Upload hallucination folder about 2 months ago
alternative_steering.py
21.8 kB
Upload folder using huggingface_hub about 2 months ago
compare_baselines.py
22.5 kB
Upload hallucination folder about 2 months ago
constants.py
2.92 kB
Upload hallucination folder about 2 months ago
cosine_gradient.py
9.15 kB
Upload hallucination folder about 2 months ago
eval_seqprobe_bce.py
8.22 kB
Upload hallucination folder about 2 months ago
gradient_ascent.py
24 kB
Upload hallucination folder about 2 months ago
gradient_ascent_generate.py
13.4 kB
Upload hallucination folder about 2 months ago
gradient_ascent_reverse.py
23 kB
Upload hallucination folder about 2 months ago
integrated_gradient.py
32.5 kB
Upload hallucination folder about 2 months ago
integrated_gradient_reverse.py
29.8 kB
Upload hallucination folder about 2 months ago
knowledge_suppression_trace.py
30 kB
Upload hallucination folder about 2 months ago
lora_a_activation.py
17.6 kB
Upload folder using huggingface_hub about 2 months ago
lora_b_steering_probes.py
11 kB
Upload hallucination folder about 2 months ago
lora_delta.py
7.06 kB
Upload hallucination folder about 2 months ago
lora_relations_sim.py
3.91 kB
Upload hallucination folder about 2 months ago
neg_cc3m.json
168 kB
Upload hallucination folder about 2 months ago
neg_cc3m_5k.json
84 kB
Upload hallucination folder about 2 months ago
per_layer_effect.py
35.4 kB
Upload hallucination folder about 2 months ago
probe_output_trace.py
18.5 kB
Upload hallucination folder about 2 months ago
probe_scoring.py
10.7 kB
Upload hallucination folder about 2 months ago
random_gradient_ascent.py
23.6 kB
Upload hallucination folder about 2 months ago
select_features.py
20.3 kB
Upload hallucination folder about 2 months ago
sequence_probe.py
7.18 kB
Upload hallucination folder about 2 months ago
toilet_retention_test.py
8.45 kB
Upload hallucination folder about 2 months ago
top_k_decode.py
7.18 kB
Upload hallucination folder about 2 months ago
train_probe_latent.py
44.2 kB
Upload hallucination folder about 2 months ago