INDEX

Explanations

references to hair and grooming characteristics

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

hair and hair-care

np_acts-logits-general · gemini-2.0-flash

hair condition, style, and loss

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 dată

-0.52

VersionUID

-0.48

чественной

-0.47

isAuthenticated

-0.46

unic

-0.45

Cey

-0.44

findpost

-0.44

 Schwarzenegger

-0.44

 cheveux

-0.44

messenger

-0.43

POSITIVE LOGITS

dressing

0.94

dress

0.86

dresser

0.80

DRESS

0.78

 loss

0.73

spray

0.71

 dresser

0.68

care

0.67

rrggbb

0.67

loss

0.67

Activations Density 0.095%

references to hair and grooming characteristics

hair and hair-care

hair condition, style, and loss

No Comments

No Known Activations