INDEX

Explanations

phrases related to authorship, funding, research studies, and conflicts of interest

oai_token-act-pair · gemini-2.0-flash

KEY

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

Negative Logits

<bos>

-0.87

 تضيفلها

-0.71

DoubleQuotes

-0.67

AddHtmlAttribute

-0.55

MessageTagHelper

-0.52

__":

-0.49

RegressionTest

-0.49

 يتيمه

-0.48

ArgsConstructor

-0.48

 Lightboxes

-0.48

POSITIVE LOGITS

+#+

0.57

hematical

0.50

 كره

0.49

ICZ

0.48

 ISNI

0.47

Chham

0.45

 ERSITY

0.45

 függ

0.45

icina

0.43

ời

0.43

Activations Density 0.577%

phrases related to authorship, funding, research studies, and conflicts of interest

KEY

No Known Activations