INDEX

Explanations

indications of starting or initiating actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

httphttps

-0.74

脚注の使い方

-0.67

:✨

-0.67

 تضيفلها

-0.53

BASEPATH

-0.52

PreferredItem

-0.51

UnitTesting

-0.50

WebControls

-0.50

ositol

-0.49

UnsafeEnabled

-0.49

POSITIVE LOGITS

 logo

0.59

logo

0.56

 Jean

0.51

Logo

0.49

 logos

0.49

Jean

0.47

 лого

0.46

IllegalArgument

0.46

 logotipo

0.45

 TAMBÉM

0.45

Activations Density 0.164%

indications of starting or initiating actions

No Comments

No Known Activations