INDEX

Explanations

the word "word" as in preface or acknowledgement, or find introductions with authors

oai_token-act-pair · gemini-2.0-flash

Introductions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fjspx

-0.59

 élevés

-0.56

 AssemblyProduct

-0.54

 getattr

-0.54

hljs

-0.53

 pério

-0.52

Posté

-0.52

 législ

-0.52

 fraî

-0.51

Dữ

-0.51

POSITIVE LOGITS

 виправивши

0.95

 disambiguazione

0.78

RenderAtEndOf

0.69

 ujednoznacz

0.67

FOREWORD

0.60

IsContent

0.58

Foreword

0.57

 consultato

0.57

はじめに

0.56

utives

0.56

Activations Density 0.969%

the word "word" as in preface or acknowledgement, or find introductions with authors

Introductions

No Comments

No Known Activations