INDEX

Explanations

references to loved ones and familial relationships

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

"ones" after "loved" or "loved ones"

np_acts-logits-general · gemini-2.0-flash

loved ones or one

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

invokeLater

-0.67

 समीक्षाओं

-0.66

SerializedSize

-0.64

 actionMode

-0.62

 Мексичка

-0.59

DateTimeField

-0.56

IsMutable

-0.56

 Roskov

-0.56

setupUi

-0.54

 Pristupljeno

-0.53

POSITIVE LOGITS

 ones

1.85

 Ones

1.66

Ones

1.40

One

1.37

ones

1.37

One

1.27

ONE

1.21

one

1.09

one

1.08

ONE

1.03

Activations Density 0.205%

references to loved ones and familial relationships

"ones" after "loved" or "loved ones"

loved ones or one

No Comments

No Known Activations