INDEX

Explanations

informative and intellectually stimulating content, particularly related to books or publications

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

books, articles, or content

np_acts-logits-general · gemini-2.0-flash

book descriptions and data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 iprot

-0.58

setupUi

-0.57

 betweenstory

-0.56

brainly

-0.55

 SIMBAD

-0.54

ukone

-0.54

 AssemblyTitle

-0.53

parseFrom

-0.53

 Impro

-0.52

amazonaws

-0.52

POSITIVE LOGITS

 Contents

0.58

 contents

0.57

 autorytatywna

0.57

Tembelea

0.56

 useful

0.56

 ouverte

0.53

ISBN

0.53

Contains

0.53

 open

0.52

Contents

0.52

Activations Density 0.263%

informative and intellectually stimulating content, particularly related to books or publications

books, articles, or content

book descriptions and data

No Comments

No Known Activations