INDEX

Explanations

instances of short phrases or markers that indicate shifts in context or sections within 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

}))

-0.59

grà

-0.53

")(

-0.52

")))

-0.52

Gam

-0.50

liothèque

-0.48

sí

-0.48

)(

-0.48

>",

-0.47

})(

-0.47

POSITIVE LOGITS

 onCreateView

0.80

 årets

0.71

jface

0.65

demic

0.63

unched

0.63

 autorytatywna

0.63

 impromptu

0.63

Последние

0.62

 craindre

0.62

 betreft

0.62

Activations Density 0.277%

instances of short phrases or markers that indicate shifts in context or sections within the text

No Comments

No Known Activations