INDEX

Explanations

data attributes and their corresponding values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

الإنجليزية

-0.88

تقاوى

-0.78

RUnlock

-0.75

 fieldNum

-0.71

(")");

-0.68

'<?

-0.67

exitRule

-0.67

 Signalez

-0.67

__':

-0.65

LookAnd

-0.64

POSITIVE LOGITS

TypedDataSet

0.47

zola

0.47

 converti

0.46

sses

0.45

Carriera

0.45

sburg

0.44

 King

0.43

isier

0.43

xsi

0.42

hyperref

0.42

Activations Density 0.161%

data attributes and their corresponding values

No Comments

No Known Activations