INDEX

Explanations

references to Google and its various services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Tikang

-0.60

 Protección

-0.60

}$)

-0.56

}*/

-0.54

ngdoc

-0.53

 שוליים

-0.50

SourceChecksum

-0.48

Gambas

-0.46

 appart

-0.46

Geplaatst

-0.45

POSITIVE LOGITS

 Chrome

0.68

Према

0.68

 searches

0.65

tserrat

0.63

ServiceTest

0.62

 Maps

0.62

enderror

0.62

LookAnd

0.61

MethodManager

0.61

Jîn

0.61

Activations Density 0.054%

references to Google and its various services or products

No Comments

No Known Activations