INDEX

Explanations

expressions of curiosity or wonder about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Datuak

-1.12

/***/

-0.76

opheles

-0.71

 Astoria

-0.70

IRQn

-0.66

beruf

-0.65

 smtplib

-0.65

 iconFacebook

-0.64

aroa

-0.64

glBindTexture

-0.63

POSITIVE LOGITS

 Wonder

1.59

 wonder

1.56

Wonder

1.55

wonder

1.52

 WONDER

1.50

 wondering

1.37

 Wonders

1.28

 wonders

1.25

 Wunder

1.23

 wondered

1.21

Activations Density 0.052%

expressions of curiosity or wonder about various topics

No Comments

No Known Activations