INDEX

Explanations

mentions of "men" or related terms in the text

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

"Men" or related terms

np_acts-logits-general · gemini-2.0-flash

men and women

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 HasFactory

-0.75

IsRequired

-0.68

 AssemblyCulture

-0.65

onActivityResult

-0.64

RuleContext

-0.63

fjspx

-0.63

EDEFAULT

-0.63

StreetMap

-0.62

İstinadlar

-0.62

localctx

-0.62

POSITIVE LOGITS

Men

1.07

MEN

1.00

Men

0.99

men

0.96

MEN

0.83

men

0.72

 Mena

0.66

 Women

0.66

Women

0.64

 WOMEN

0.64

Activations Density 0.075%

mentions of "men" or related terms in the text

"Men" or related terms

men and women

No Comments

No Known Activations