INDEX

Explanations

mentions of the United States

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

Efq

-0.71

 NSCoder

-0.68

 متعلقه

-0.67

 myſelf

-0.63

 itſelf

-0.61

 poffe

-0.59

 whoſe

-0.59

 mergeFrom

-0.57

 reaſon

-0.56

sidemargin

-0.56

POSITIVE LOGITS

 States

1.15

 Kingdom

0.87

 Nations

0.83

 United

0.83

States

0.80

 states

0.79

 STATES

0.78

United

0.71

 kingdom

0.69

Kingdom

0.69

Activations Density 0.079%

mentions of the United States

No Comments

No Known Activations