INDEX

Explanations

phrases, terminology, and symbols related to programming and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 الحره

-0.52

]){

-0.46

BER

-0.42

 Mount

-0.41

niana

-0.40

 kohdetta

-0.39

 ?>">

-0.39

[]=$

-0.37

?>">

-0.37

Mount

-0.36

POSITIVE LOGITS

bootstrapcdn

0.75

 AssemblyCulture

0.63

shadowRadius

0.57

 onPostExecute

0.53

DispatchToProps

0.52

ItemBackground

0.51

ClientSize

0.50

StoryboardSegue

0.49

Rüyada

0.49

 Infórmanos

0.49

Activations Density 2.050%

phrases, terminology, and symbols related to programming and data manipulation

No Comments

No Known Activations