INDEX

Explanations

references to individuals involved in chess problem composition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 purpoſe

-0.32

 occaf

-0.30

 quæ

-0.29

 defire

-0.29

 theſe

-0.29

 himſelf

-0.29

chaffenheit

-0.29

 itſelf

-0.28

 pleaſure

-0.28

 people

-0.28

POSITIVE LOGITS

 ویکی‌پدی

0.78

 Meksiku

0.62

avadoc

0.62

@"/

0.59

 autorytatywna

0.58

DeleteBehavior

0.57

LEncoder

0.56

 pinulongan

0.55

writeHead

0.54

attutto

0.53

Activations Density 1.985%

references to individuals involved in chess problem composition

No Comments

No Known Activations