INDEX

Explanations

references and citations within academic texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للمعارف

-0.62

 تانيه

-0.62

Portály

-0.58

underbrace

-0.56

byr

-0.54

Personensuche

-0.54

لیس

-0.54

RenderAtEndOf

-0.52

FunctionFlags

-0.52

 الرياضيه

-0.52

POSITIVE LOGITS

xxi

0.75

xii

0.74

 xxiv

0.73

xiv

0.73

xix

0.73

 xviii

0.70

xvi

0.69

 xvii

0.69

 passim

0.69

 xiii

0.69

Activations Density 0.255%

references and citations within academic texts

No Comments

No Known Activations