INDEX

Explanations

references to programming and coding functions or methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

verwijspagina

-0.73

 '\\;'

-0.71

abestanden

-0.67

featureID

-0.67

 disambiguazione

-0.66

 näky

-0.66

 propOrder

-0.64

AutoScale

-0.64

djangoproject

-0.62

 RoutedEventArgs

-0.61

POSITIVE LOGITS

shiro

0.53

endphp

0.46

行政区划

0.45

 ModelExpression

0.45

 Hotspur

0.42

 całość

0.39

oa̍t

0.37

module

0.37

 Transcript

0.36

式的

0.36

Activations Density 0.441%

references to programming and coding functions or methods

No Comments

No Known Activations