INDEX

Explanations

phrases indicating topics of discussion or central themes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himſelf

-0.80

 houſe

-0.78

 itſelf

-0.77

 Reſ

-0.76

 Conſ

-0.75

ſelf

-0.74

 russes

-0.74

 Diſ

-0.73

 poffe

-0.73

 ſtate

-0.70

POSITIVE LOGITS

 ABOUT

1.29

 about

1.28

ABOUT

1.27

Bout

1.17

 Bout

1.16

abt

1.16

 About

1.15

About

1.07

bout

1.05

antMatchers

1.02

Activations Density 0.104%

phrases indicating topics of discussion or central themes

No Comments

No Known Activations