INDEX

Explanations

instances where the text encourages further reading or exploration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

kháu

-0.50

 intr

-0.49

 QtGui

-0.49

int

-0.48

 MenuView

-0.48

onAttach

-0.47

出版年

-0.47

too

-0.46

Składniki

-0.46

sentry

-0.46

POSITIVE LOGITS

 متعلقه

0.85

ModelAdmin

0.75

ंदीखरीदारी

0.71

 Theſe

0.71

 Профиль

0.68

++]=

0.67

SharedCtor

0.65

 ویکی‌پدی

0.63

 Biôgrafia

0.63

 Corsica

0.63

Activations Density 0.128%

instances where the text encourages further reading or exploration

No Comments

No Known Activations