INDEX

Explanations

numerical data and statistical outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

IPPING

-0.52

Gotcha

-0.50

bite

-0.46

 eating

-0.45

 kicking

-0.45

 dressing

-0.45

 ajutor

-0.44

 shooting

-0.43

 quema

-0.43

 hitting

-0.43

POSITIVE LOGITS

LookAnd

0.75

ंदीखरीदारी

0.65

GEBURTSDATUM

0.64

Personendaten

0.63

 onCreateView

0.60

ArgumentParser

0.59

Geografía

0.57

例文帳に追加

0.57

hbs

0.57

Hozzáférés

0.56

Activations Density 0.430%

numerical data and statistical outputs

No Comments

No Known Activations