INDEX

Explanations

intense emotions and aggressive language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

toppers

-0.64

?).

-0.58

?')

-0.58

uhi

-0.57

tzmann

-0.56

 насеље

-0.56

 vieles

-0.56

Portály

-0.55

 вроде

-0.55

XmlAccessorType

-0.54

POSITIVE LOGITS

🖕

0.79

 motherfucker

0.73

 autorytatywna

0.68

 bitch

0.67

 dares

0.64

 fucker

0.63

 insol

0.63

黙

0.61

 fucking

0.60

 fuck

0.60

Activations Density 0.150%

intense emotions and aggressive language

No Comments

No Known Activations