INDEX

Explanations

mathematical expressions and variables

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

 Administrativna

-0.64

werben

-0.52

يكب

-0.50

<?

-0.49

 stali

-0.49

queles

-0.49

 Grüsse

-0.47

原始内容存档于

-0.47

 quedado

-0.46

 península

-0.45

POSITIVE LOGITS

awtextra

0.57

OGND

0.54

 Numerade

0.48

rungsseite

0.45

 pinulongan

0.44

.}~\

0.41

getHours

0.40

Tikang

0.39

 nahilalakip

0.38

).—

0.38

Activations Density 0.105%

mathematical expressions and variables

No Comments

No Known Activations