145 kB

Ctrl+K

1 contributor

History: 2 commits

ToiTenBao

Upload folder using huggingface_hub

299fd20 verified about 2 months ago

alternative_steering.sh

3.52 kB
Upload hallucination folder about 2 months ago
compare_baselines.sh

4.97 kB
Upload hallucination folder about 2 months ago
confirm_features_patching.sh

6.54 kB
Upload hallucination folder about 2 months ago
correlation_baselines.sh

2.83 kB
Upload hallucination folder about 2 months ago
cosine_gradient.sh

1.97 kB
Upload hallucination folder about 2 months ago
d_sae_correlation_patching.sh

6.43 kB
Upload hallucination folder about 2 months ago
delta_w_feature_trace.sh

4.61 kB
Upload hallucination folder about 2 months ago
diff_gradient_ascent.py

1.93 kB
Upload hallucination folder about 2 months ago
gradient_ascent.sh

5.45 kB
Upload hallucination folder about 2 months ago
gradient_ascent_generate.sh

3.38 kB
Upload hallucination folder about 2 months ago
gradient_ascent_reverse.sh

4.06 kB
Upload hallucination folder about 2 months ago
hallucination.sh

3.73 kB
Upload hallucination folder about 2 months ago
integrated_gradient.sh

6.79 kB
Upload hallucination folder about 2 months ago
integrated_gradient_reverse.sh

4.91 kB
Upload hallucination folder about 2 months ago
kl_coherence_others.sh

4.23 kB
Upload folder using huggingface_hub about 2 months ago
kl_coherence_toilet.sh

4.23 kB
Upload folder using huggingface_hub about 2 months ago
knowledge_suppression_trace.sh

4.62 kB
Upload hallucination folder about 2 months ago
mlp_trace_features.sh

5.55 kB
Upload hallucination folder about 2 months ago
mlp_trace_probe.sh

4.71 kB
Upload hallucination folder about 2 months ago
patching.sh

1.97 kB
Upload hallucination folder about 2 months ago
per_layer_effect.sh

4.42 kB
Upload hallucination folder about 2 months ago
plot_probe_latent_metrics.py

3.17 kB
Upload hallucination folder about 2 months ago
plot_probe_latent_metrics.sh

920 Bytes
Upload hallucination folder about 2 months ago
plot_variant_auc.sh

1.04 kB
Upload hallucination folder about 2 months ago
probe_output_trace.sh

3.98 kB
Upload hallucination folder about 2 months ago
probe_scoring.sh

4.13 kB
Upload hallucination folder about 2 months ago
push_latent_probes.sh

2.82 kB
Upload hallucination folder about 2 months ago
random_gradient_ascent.sh

4.09 kB
Upload hallucination folder about 2 months ago
replot_gradient_ascent.py

4.53 kB
Upload hallucination folder about 2 months ago
run_4feat_edits_chain.sh

2.27 kB
Upload hallucination folder about 2 months ago
run_gradient_ascent_all.sh

3.12 kB
Upload hallucination folder about 2 months ago
run_probe_latent_wait.sh

3.37 kB
Upload hallucination folder about 2 months ago
select_features.sh

5.85 kB
Upload hallucination folder about 2 months ago
train_probe_latent.sh

12.5 kB
Upload hallucination folder about 2 months ago
write_seqprobe_metrics_md.py

2.28 kB
Upload hallucination folder about 2 months ago