INDEX

Explanations

references to phones and phone-related objects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

存于互联网档案馆

-0.92

zitter

-0.71

Siv

-0.68

 Steinberg

-0.67

daging

-0.66

 Asie

-0.65

 Trit

-0.65

 الحره

-0.64

ẋ

-0.63

Zit

-0.62

POSITIVE LOGITS

 phone

1.56

 phones

1.55

 Phone

1.45

 PHONE

1.44

 telephone

1.32

getPhone

1.32

 Phones

1.31

PHONE

1.30

Phone

1.29

phone

1.27

Activations Density 0.064%

references to phones and phone-related objects or concepts

No Comments

No Known Activations