INDEX

Explanations

references to different worlds, realities, or fantastical settings within narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•Literature

references to different worlds, realities, or fantastical settings within narratives

No Comments

Negative Logits

MLLoader

-0.55

 estekak

-0.54

annin

-0.50

ücksich

-0.50

AndEndTag

-0.50

artifactId

-0.48

ValueGenerated

-0.48

HasIndex

-0.48

 jsPsych

-0.48

addGap

-0.47

POSITIVE LOGITS

 world

2.18

world

1.90

 worlds

1.84

 universe

1.65

 mundo

1.60

 WORLD

1.55

WORLD

1.50

 World

1.46

worlds

1.46

World

1.45

Activations Density 0.319%

references to different worlds, realities, or fantastical settings within narratives

No Comments

No Known Activations