INDEX

Explanations

instances of the pronoun "he" or related terms indicating gender

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

"he/she" or similar gender-neutral pronouns

np_acts-logits-general · gemini-2.0-flash

he/she or he or she

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

StoryboardSegue

-1.02

 Biôgrafia

-0.94

GraphicsUnit

-0.94

UnsafeEnabled

-0.91

 Paglinawan

-0.88

 protoimpl

-0.87

PreferredItem

-0.86

Sucesor

-0.84

 Roskov

-0.83

Hentet

-0.82

POSITIVE LOGITS

his

0.47

 חיצוניים

0.47

 dumne

0.46

She

0.42

hers

0.40

 whom

0.40

her

0.40

 señ

0.39

his

0.38

rum

0.38

Activations Density 0.139%

instances of the pronoun "he" or related terms indicating gender

"he/she" or similar gender-neutral pronouns

he/she or he or she

No Comments

No Known Activations