INDEX

Explanations

phrases related to books and their various attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

bustible

-0.62

الإنجليزية

-0.55

abestanden

-0.54

istoitu

-0.53

guet

-0.51

 Krzyż

-0.50

cæ

-0.50

vdash

-0.50

 écoulé

-0.50

tamol

-0.49

POSITIVE LOGITS

 StatelessWidget

0.73

Cyfarwyddwr

0.63

 StatefulWidget

0.62

 EventArgs

0.62

Šaltiniai

0.62

stateProvider

0.59

 referenties

0.57

digkeit

0.56

WaitGroup

0.55

Activations Density 0.228%

phrases related to books and their various attributes

No Comments

No Known Activations