INDEX

Explanations

function or testing-related keywords and phrases

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

enumi

-0.96

Personendaten

-0.83

IsMutable

-0.81

 المعيارى

-0.79

ConstraintMaker

-0.68

sizeCache

-0.68

LayoutStyle

-0.67

 RoutedEventArgs

-0.66

transQ

-0.65

aarrggbb

-0.64

POSITIVE LOGITS

 disambiguazione

0.54

igheid

0.52

achs

0.52

getRole

0.48

Gad

0.46

rungsseite

0.45

 could

0.45

……"

0.44

 that

0.44

Nationalité

0.44

Activations Density 0.043%

function or testing-related keywords and phrases

No Comments

No Known Activations