INDEX

Explanations

quantitative data and numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 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

 informée

-0.60

GEBURTSDATUM

-0.60

Portály

-0.60

Autoritní

-0.54

 للاسماء

-0.53

QMetaType

-0.52

 jScrollPane

-0.52

 contextLoads

-0.52

adaptiveStyles

-0.51

 CallOverrides

-0.50

POSITIVE LOGITS

Bio

0.47

 Extra

0.42

 INDUSTRIAL

0.41

bio

0.40

BIO

0.40

 Paglinawan

0.40

 régulier

0.39

 industrial

0.39

emptory

0.39

 industriel

0.39

Activations Density 1.405%

quantitative data and numerical information

No Comments

No Known Activations