INDEX

Explanations

references to specific topics, subjects, or cases being discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ftagPool

-0.86

 itſelf

-0.76

AxisAlignment

-0.68

 Мексичка

-0.66

 Reisedaten

-0.63

ंदीखरीदारी

-0.63

 createSprite

-0.63

¢

-0.63

følgelig

-0.62

 Houſe

-0.61

POSITIVE LOGITS

 them

0.49

APORE

0.48

 Klicken

0.47

achev

0.46

enumii

0.46

it

0.45

 ellos

0.44

Compiled

0.44

rawd

0.43

Activations Density 0.956%

references to specific topics, subjects, or cases being discussed

No Comments

No Known Activations