INDEX

Explanations

references to family members and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ंदीखरीदारी

-0.55

 مرئيه

-0.54

tagHelperRunner

-0.48

 eſſ

-0.47

 esercit

-0.45

 ordinaires

-0.45

Carriera

-0.45

 mauva

-0.44

LookAnd

-0.43

 ProtoMessage

-0.43

POSITIVE LOGITS

awesome

0.41

 families

0.40

happ

0.39

IGraphics

0.37

AMILY

0.37

host

0.37

families

0.37

PYX

0.37

team

0.37

 happiest

0.36

Activations Density 0.075%

references to family members and relationships

No Comments

No Known Activations