INDEX

Explanations

punctuation marks and formatting indicators

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.89

PerformLayout

-0.75

 IBOutlet

-0.74

abestanden

-0.69

InputBorder

-0.65

RenderAtEndOf

-0.63

openConnection

-0.63

 AssemblyCompany

-0.63

 PopupWindow

-0.63

Filmografia

-0.62

POSITIVE LOGITS

And

0.49

 ویکی‌پدی

0.47

 inconn

0.47

 vicenda

0.45

 nyata

0.45

 marquer

0.45

())));

0.44

 szolgált

0.44

dip

0.43

 hiszen

0.43

Activations Density 0.801%

punctuation marks and formatting indicators

No Comments

No Known Activations