INDEX

Explanations

terms related to attention and its measurement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 ویکی‌پدی

-1.52

 kaarangay

-1.41

 autorytatywna

-1.36

 betweenstory

-1.34

uxxxx

-1.27

 nahilalakip

-1.26

 Administrativna

-1.24

 Roskov

-1.21

 noDo

-1.20

 Taktlose

-1.16

POSITIVE LOGITS

is

0.39

0.37

 from

0.35

GenerationType

0.34

and

0.34

Slf

0.34

 trend

0.33

to

0.33

0.32

0.31

Activations Density 5.304%

terms related to attention and its measurement in various contexts

No Comments

No Known Activations