INDEX

Explanations

phrases indicating quantity or expressions of ranking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Portály

-0.52

 Flüssigkeit

-0.50

eschön

-0.49

rachtet

-0.48

withOpacity

-0.48

chengladbach

-0.48

IBLIO

-0.47

 kenyataan

-0.46

ydable

-0.45

phorbia

-0.45

POSITIVE LOGITS

oneof

0.76

 among

0.63

GEBURTSDATUM

0.58

 member

0.56

among

0.56

 Member

0.54

 أحد

0.54

 Among

0.54

 amongst

0.53

 highly

0.52

Activations Density 0.135%

phrases indicating quantity or expressions of ranking

No Comments

No Known Activations