INDEX

Explanations

sections of code and markup where descriptions and specifications are provided

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 utafitiHapana

-0.73

 betweenstory

-0.55

usda

-0.54

ImageContext

-0.53

Referencie

-0.53

 Vikipedi

-0.52

 Taus

-0.50

 словом

-0.50

Tils

-0.49

ownic

-0.49

POSITIVE LOGITS

出版年

0.73

featureID

0.64

ValueStyle

0.62

>{@

0.60

elemField

0.57

SourceChecksum

0.56

EndInit

0.55

HomeAsUpEnabled

0.54

__(/*!

0.54

λίου

0.53

Activations Density 0.131%

sections of code and markup where descriptions and specifications are provided

No Comments

No Known Activations