INDEX

Explanations

references to accuracy and precision in measurements or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

AnchorStyles

-0.67

盪

-0.63

蕩

-0.62

 menga

-0.61

пети

-0.58

 Gosling

-0.58

li

-0.56

 Fish

-0.56

 partidos

-0.55

Bo

-0.55

POSITIVE LOGITS

 accuracy

1.75

 Accuracy

1.62

 Accurate

1.55

Accurate

1.52

 ACCUR

1.52

 accurate

1.51

accuracy

1.44

Accuracy

1.43

accurate

1.37

 precision

1.35

Activations Density 0.081%

references to accuracy and precision in measurements or assessments

No Comments

No Known Activations