INDEX

Explanations

phrases that include articles describing people or their roles

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

 pungkasnya

-0.50

gebung

-0.50

uebe

-0.49

 elaborate

-0.49

wurf

-0.48

 Rücks

-0.48

Jeografia

-0.48

 Eggers

-0.47

 Schluss

-0.47

ssohn

-0.46

POSITIVE LOGITS

richTextPanel

0.58

 ModelExpression

0.42

transQ

0.40

 userType

0.36

staticmethod

0.36

超级

0.35

 SUPER

0.35

createCanvas

0.35

 Profession

0.34

 onlyOwner

0.34

Activations Density 0.235%

phrases that include articles describing people or their roles

No Comments

No Known Activations