INDEX

Explanations

terms related to pregnancy and maternal health

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

preceding "women"

np_acts-logits-general · gemini-2.0-flash

pregnant women

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

Male

-1.00

 Male

-0.99

 männ

-0.98

 MALE

-0.90

 Gender

-0.88

MALE

-0.87

CHILD

-0.81

male

-0.81

 masculina

-0.81

 Female

-0.79

POSITIVE LOGITS

 women

1.28

 wonen

0.98

 phụ

0.62

wo

0.61

women

0.56

 vrouwen

0.55

 հղումներ

0.54

بوابة

0.54

ArgumentParser

0.53

PerformLayout

0.53

Activations Density 0.184%

terms related to pregnancy and maternal health

preceding "women"

pregnant women

No Comments

No Known Activations