INDEX

Explanations

phrases indicating the conclusion or end of events or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

帖最后由

-0.70

 transférez

-0.69

 nahilalakip

-0.69

 magasiner

-0.69

ckså

-0.67

__);

-0.65

casian

-0.63

appartamento

-0.60

évaluateur

-0.59

ècie

-0.59

POSITIVE LOGITS

end

1.05

 ends

0.97

EndOf

0.97

End

0.95

 Ends

0.94

 Ende

0.91

END

0.91

End

0.90

 конце

0.83

末

0.82

Activations Density 0.139%

phrases indicating the conclusion or end of events or time periods

No Comments

No Known Activations