INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Bob

-0.47

OMBIA

-0.44

เ

-0.43

instellungen

-0.42

wwe

-0.41

 Tirol

-0.41

Buenas

-0.41

Bob

-0.40

spedes

-0.40

bob

-0.39

POSITIVE LOGITS

elemField

0.55

SourceChecksum

0.51

XmlAccessorType

0.50

ViewImports

0.50

+#+

0.50

UnitTesting

0.49

 initComponents

0.48

istoitu

0.45

 anuales

0.43

XmlEnum

0.42

Activations Density 0.648%

references to academic journals and publications

No Comments

No Known Activations