INDEX

Explanations

references to young girls and boys

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

"boy" or "girl"

np_acts-logits-general · gemini-2.0-flash

boy or girl

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 EconPapers

-0.50

httphttps

-0.49

/**

-0.47

ruptcy

-0.47

역사

-0.47

inerary

-0.47

unak

-0.47

 Hennessy

-0.46

anyahu

-0.44

menopausal

-0.44

POSITIVE LOGITS

boy

1.77

 girl

1.72

 boys

1.69

 girls

1.68

Girls

1.59

 Girls

1.59

Girl

1.58

girls

1.58

 Girl

1.55

Boys

1.55

Activations Density 0.092%

references to young girls and boys

"boy" or "girl"

boy or girl

No Comments

No Known Activations