INDEX

Explanations

phrases and titles of works, particularly those related to books or documentaries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

IntoConstraints

-0.63

FunctionFlags

-0.57

IUrlHelper

-0.56

aarrggbb

-0.54

 auroit

-0.54

 intStringLen

-0.51

webElement

-0.51

 Numerade

-0.50

 Italijani

-0.50

Tikang

-0.49

POSITIVE LOGITS

“

0.53

«

0.50

‘

0.47

 ‘‘

0.45

0.43

‘

0.42

 ‘’

0.40

/**

0.40

}{*}{

0.40

CPtr

0.39

Activations Density 0.376%

phrases and titles of works, particularly those related to books or documentaries

No Comments

No Known Activations