INDEX

Explanations

company names and locations

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

Not in Any Lists

No Comments

Negative Logits

rovnik

-0.56

 SwiftUI

-0.56

 Pyongyang

-0.50

 ModelExpression

-0.49

 Hanoi

-0.49

 Référence

-0.48

 Moab

-0.46

ودی

-0.46

 Cornish

-0.46

efe

-0.46

POSITIVE LOGITS

USA

1.10

USA

0.97

 United

0.90

UK

0.84

United

0.79

Usa

0.76

usa

0.75

 Australia

0.73

US

0.70

 Canada

0.70

Activations Density 0.282%

company names and locations

No Comments

No Known Activations