INDEX

Explanations

questions or inquiries within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CascadeType

-0.41

CloseOperation

-0.34

whenever

-0.33

 ligiloj

-0.33

chafter

-0.32

 cauza

-0.29

 demografica

-0.29

okolade

-0.29

opold

-0.29

="@+

-0.29

POSITIVE LOGITS

VYMaps

0.52

 better

0.52

 createState

0.50

 المعيارى

0.49

Diwedd

0.49

 sitten

0.48

AnimationsModule

0.47

GEBURTSDATUM

0.47

addContainerGap

0.46

 really

0.45

Activations Density 0.145%

questions or inquiries within the text

No Comments

No Known Activations