INDEX

Explanations

references and citation-related elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 ideal

-0.34

-0.32

 blind

-0.32

Ele

-0.30

áo

-0.30

 Blom

-0.29

 adaptation

-0.28

te

-0.28

jau

-0.28

Cob

-0.27

POSITIVE LOGITS

rawDesc

0.98

ViewFeatures

0.93

 AssemblyCulture

0.92

GEBURTSDATUM

0.92



0.85

 tartalomajánló

0.85

 AssemblyTitle

0.83

 للاسماء

0.82

ScopeManager

0.82

featureID

0.82

Activations Density 0.339%

references and citation-related elements in the text

No Comments

No Known Activations