INDEX

Explanations

phrases related to discussions or statements made by individuals, particularly in a press or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 kasarigan

-0.77

 havaianas

-0.61

 linkovi

-0.52

 Audiodateien

-0.52

 MenuView

-0.50

chengladbach

-0.50

ModelSerializer

-0.48

ükü

-0.47

Cependant

-0.46

/>\

-0.46

POSITIVE LOGITS

脚注の使い方

0.80

 تضيفلها

0.78

 مشين

0.74

 nahilalakip

0.73

abestanden

0.71

 <<<<<<<<<<<<<<

0.68

 المعيارى

0.62

DoubleQuotes

0.62

">//

0.62

 وتسجيلات

0.60

Activations Density 0.077%

phrases related to discussions or statements made by individuals, particularly in a press or formal context

No Comments

No Known Activations