INDEX

Explanations

words related to modification or denouncing something

oai_token-act-pair · gemini-2.0-flash

removing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

siella

-0.56

})`

-0.54

Brainz

-0.50

 noticia

-0.49

IAction

-0.47

 ***!

-0.47

судар

-0.47

anasia

-0.46

 tassel

-0.44

WebServlet

-0.43

POSITIVE LOGITS

تقاوى

0.60

 ویکی‌پدیای

0.59

 насељу

0.56

لينكات

0.55

ToAction

0.54

SequentialGroup

0.54

setColumns

0.54

 intermédiaire

0.54

CloseOperation

0.54

SizeMode

0.53

Activations Density 1.146%

words related to modification or denouncing something

removing

No Comments

No Known Activations