INDEX

Explanations

references to the United States in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 alder

-0.80

styleType

-0.80

 Tafel

-0.75

 Tinker

-0.74

Gera

-0.74

 Credential

-0.74

 Tack

-0.73

^^^^^^^^

-0.71

CreateModel

-0.71

 Colli

-0.70

POSITIVE LOGITS

US

2.06

US

1.68

USA

1.25

Us

1.19

us

1.17

 United

1.11

 States

1.11

UK

1.06

 EEUU

1.01

 states

0.95

Activations Density 0.093%

references to the United States in various contexts

No Comments

No Known Activations