INDEX

Explanations

references to specific dates, times, and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

@"/

-0.34

slidesPer

-0.29

 Usaha

-0.25

 temprano

-0.23

HandlerContext

-0.23

verticalLayout

-0.22

 Gesellschaft

-0.22

RunAsync

-0.22

 morada

-0.22

.*")]

-0.21

POSITIVE LOGITS

 ویکی‌پدی

0.73

ſchaft

0.72

 kasarigan

0.69

 stiefe

0.68

iſchen

0.67

SOUNDBITE

0.66

 好文分享

0.66

஦

0.66

 ſeinen

0.66

niſſe

0.66

Activations Density 0.531%

references to specific dates, times, and numerical data

No Comments

No Known Activations