INDEX

Explanations

formatting markers or structural elements in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

‘

-0.55

’

-0.47

”

-0.46

</em>

-0.46

“

-0.46

terase

-0.42

akterysty

-0.41

zboi

-0.40

Sidenav

-0.40

-0.39

POSITIVE LOGITS

 виправивши

1.12

ValueStyle

1.01

 autorytatywna

0.99

 تضيفلها

0.95

AccessorTable

0.93

NameInMap

0.92

awtextra

0.89

Aholisi

0.85

Personensuche

0.85

@[+][

0.83

Activations Density 0.591%

formatting markers or structural elements in data

No Comments

No Known Activations