INDEX

Explanations

phrases indicating requests for more information or additional data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 resourceCulture

-0.80

دانشنامهٔ

-0.78

ImageContext

-0.70

 photolibrary

-0.67

ClientRect

-0.65

 betweenstory

-0.64

 Philist

-0.64

Espèce

-0.64

Identyfik

-0.64

 makeStyles

-0.63

POSITIVE LOGITS

To

0.65

Чтобы

0.56

 Чтобы

0.56

 continúas

0.55

Για

0.55

For

0.54

To

0.50

gre

0.50

appcompat

0.49

adj

0.49

Activations Density 0.268%

phrases indicating requests for more information or additional data

No Comments

No Known Activations