INDEX

Explanations

references to authorship and contributions in a scholarly context

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

preface, foreword, acknowledgements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 FetchType

-0.59

Искәрмәләр

-0.56

 فريبيس

-0.56

!*\

-0.54

 linkovi

-0.52

Tembelea

-0.50

 للمعارف

-0.48

Tamb

-0.48

Must

-0.47

uthorized

-0.46

POSITIVE LOGITS

CONTENIDO

0.46

RTEE

0.44

addCriterion

0.38

engager

0.36

ResumeLayout

0.36

engagent

0.35

 readers

0.35

FOREWORD

0.34

äfts

0.34

Geschiedenis

0.33

Activations Density 0.033%

references to authorship and contributions in a scholarly context

preface, foreword, acknowledgements

No Comments

No Known Activations