INDEX

Explanations

patterns or markers in numerical data or structured information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

in

-0.64

zu

-0.64

im

-0.62

to

-0.60

 pres

-0.59

mot

-0.59

kan

-0.59

${

-0.57

-0.56

sem

-0.56

POSITIVE LOGITS

 myſelf

1.46

 itſelf

1.42

 ſtate

1.32

 ſmall

1.28

 Anſ

1.27

 pleaſure

1.26

 greateſt

1.25

 doubtnut

1.25

Efq

1.23

 Houſe

1.22

Activations Density 1.196%

patterns or markers in numerical data or structured information

No Comments

No Known Activations