INDEX

Explanations

no relevant content or activation in the document

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

after "The" or "end"

np_acts-logits-general · gemini-2.0-flash

end . derivative

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

AsUp

-0.91

 TextAppearance

-0.91

WithIOException

-0.87

 jScrollPane

-0.81

QMetaType

-0.73

 Paglinawan

-0.73

Jeografia

-0.72

########.

-0.71

 FetchType

-0.71

 Biôgrafia

-0.70

POSITIVE LOGITS

center

0.54

щами

0.50

End

0.50

end

0.48

\\

0.44

setEnd

0.43

 jude

0.43

\[

0.43

eun

0.43

itemize

0.43

Activations Density 0.002%

no relevant content or activation in the document

after "The" or "end"

end . derivative

No Comments

No Known Activations