INDEX

Explanations

references to individuals, particularly males and females, often characterized by age or role

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 budget

-0.59

vœ

-0.57

爱的

-0.55

uç

-0.55

 cauza

-0.54

 autorytatywna

-0.54

budget

-0.53

 drenaje

-0.53

intl

-0.52

 fontes

-0.52

POSITIVE LOGITS

who

1.03

 whom

0.73

man

0.72

apimachinery

0.69

 dude

0.68

 gentleman

0.68

 SqlCommand

0.67

SourceChecksum

0.66

 person

0.66

 mans

0.66

Activations Density 0.038%

references to individuals, particularly males and females, often characterized by age or role

No Comments

No Known Activations