INDEX

Explanations

phrases related to explosive or impactful events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Normdatei

-1.14

ImageContext

-0.71

QMetaType

-0.66

abetes

-0.64

اریخ

-0.63

 TType

-0.61

WaitGroup

-0.60

GOTREF

-0.58

WireFormatLite

-0.57

出版年

-0.57

POSITIVE LOGITS

 blown

1.30

 blow

1.24

 blew

1.22

blown

1.16

Blow

1.15

 blows

1.14

 Blow

1.12

 blowing

1.07

blow

1.00

blowing

0.92

Activations Density 0.058%

phrases related to explosive or impactful events

No Comments

No Known Activations