INDEX

Explanations

formats or markdown syntax used in technical documents

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

«

-0.59

-0.56

-0.55

“

-0.52

 both

-0.51

-0.47

<eos>

-0.46

—

-0.46

et

-0.45

–

-0.45

POSITIVE LOGITS

Personendaten

1.25

 للاسماء

0.99

GEBURTSDATUM

0.96

awtextra

0.95

 purpoſe

0.93

 greateſt

0.93

NameInMap

0.92

IntoConstraints

0.92

 Italijanski

0.91

 kaarangay

0.88

Activations Density 0.274%

formats or markdown syntax used in technical documents

No Comments

No Known Activations