INDEX

Explanations

phrases related to geographical descriptions and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

and

-0.95

or

-0.72

性和

-0.72

EndContext

-0.64

Personendaten

-0.61

مراجع

-0.58

ագրություններ

-0.57

MENAFN

-0.57

Життєпис

-0.57

المراجع

-0.55

POSITIVE LOGITS

 alike

0.74

อื่น

0.62

 utafitiHapana

0.57

OGRAPH

0.56

 दोनों

0.55

译

0.54

denly

0.54

 تضيفلها

0.52

QUENCE

0.52

何より

0.52

Activations Density 4.505%

phrases related to geographical descriptions and attributes

No Comments

No Known Activations