INDEX

Explanations

phrases related to performance and competition among individuals or groups

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

 Snow

-0.29

Gir

-0.27

قایناق‌لار

-0.27

obt

-0.27

irited

-0.27

 Rest

-0.26

 Allow

-0.26

 protoimpl

-0.26

expect

-0.26

 Auge

-0.26

POSITIVE LOGITS

تقاوى

0.73

SequentialGroup

0.61

новништво

0.57

 مشين

0.56

pushFollow

0.55

ⓧ

0.55

 الرياضيه

0.54

uxxxx

0.54

 himself

0.52

 surla

0.52

Activations Density 0.901%

phrases related to performance and competition among individuals or groups

No Comments

No Known Activations