INDEX

Explanations

references to the concept of "world" and its variations or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 Ryanair

-0.85

 للاسماء

-0.81

Xie

-0.80

 Mortar

-0.80

 desta

-0.79

 Cottages

-0.79

 Notary

-0.77

 Tattoos

-0.76

 Pilate

-0.75

 Amtrak

-0.74

POSITIVE LOGITS

 World

1.99

 world

1.98

 WORLD

1.83

World

1.78

world

1.71

WORLD

1.64

 Worlds

1.56

 worlds

1.55

orld

1.52

Worlds

1.51

Activations Density 0.042%

references to the concept of "world" and its variations or implications

No Comments

No Known Activations