INDEX

Explanations

descriptions of physical appearance, particularly focusing on hair attributes and styles

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

actionMode

-0.53

colgroup

-0.51

saraba

-0.46

ulement

-0.44

 fuite

-0.44

graphique

-0.44

niaus

-0.43

商品説明

-0.42

 ausgeschlossen

-0.42

 thèse

-0.41

POSITIVE LOGITS

 hair

1.91

 Hair

1.62

hair

1.62

 HAIR

1.59

Hair

1.56

HAIR

1.41

 hairstyle

1.38

 hairs

1.32

 hairstyles

1.32

 haircut

1.30

Activations Density 0.084%

descriptions of physical appearance, particularly focusing on hair attributes and styles

No Comments

No Known Activations