INDEX

Explanations

references to paragraphs and paragraph formatting in text

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

 Administrativna

-0.58

 Keuangan

-0.54

tvguidetime

-0.50

Lähteet

-0.49

RTDA

-0.48

strument

-0.46

Wu

-0.46

 propOrder

-0.46

 informée

-0.46

WU

-0.45

POSITIVE LOGITS

par

1.88

Par

1.84

par

1.70

Par

1.69

PAR

1.63

PAR

1.43

 Para

1.30

 para

1.27

 пара

1.23

 Parr

1.18

Activations Density 0.146%

references to paragraphs and paragraph formatting in text

No Comments

No Known Activations