INDEX

Explanations

references to phones and phone-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

存于互联网档案馆

-1.09

zitter

-0.72

 Steinberg

-0.71

daging

-0.71

 Asie

-0.69

 Gatsby

-0.68

Siv

-0.67

 Trit

-0.66

Giveaway

-0.66

ίων

-0.65

POSITIVE LOGITS

 phone

1.62

 phones

1.57

 Phone

1.49

 PHONE

1.47

 telephone

1.36

PHONE

1.34

getPhone

1.33

Phone

1.33

phone

1.30

 telephones

1.29

Activations Density 0.048%

references to phones and phone-related activities

No Comments

No Known Activations