INDEX

Explanations

questions starting with "how."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Personensuche

-0.86

ंदीखरीदारी

-0.84

 дописавши

-0.78

 Cæsar

-0.72

VersionUID

-0.69

SceneManagement

-0.68

 unknownFields

-0.68

)_/¯

-0.67

DotNetBar

-0.63

IntoConstraints

-0.62

POSITIVE LOGITS

 much

0.92

 exactly

0.74

we

0.70

how

0.70

itzer

0.70

to

0.70

much

0.66

 they

0.64

far

0.64

HOW

0.63

Activations Density 0.074%

questions starting with "how."

No Comments

No Known Activations