INDEX

Explanations

phrases indicating conclusions or summaries in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Véxase

-0.71

spli

-0.66

 Gabriela

-0.65

Trev

-0.64

 Herz

-0.63

 EINVAL

-0.62

andu

-0.62

SP

-0.60

Bur

-0.60

Filmografie

-0.59

POSITIVE LOGITS

 conclusions

1.25

 conclusion

1.18

impulan

1.09

 Conclusions

1.09

conclusion

1.07

 conclude

1.07

 concludes

0.94

 Conclusion

0.91

 conclusión

0.90

 CONCLUSION

0.90

Activations Density 0.092%

phrases indicating conclusions or summaries in the text

No Comments

No Known Activations