INDEX

Explanations

a mix of HTML tags, words associated with academic publications, and the word "Created"

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 purpoſe

-0.52

 becauſe

-0.50

AddTagHelper

-0.47

 Theſe

-0.46

ⓧ

-0.46

 itſelf

-0.46

 myſelf

-0.45

Efq

-0.44

 ſeveral

-0.44

 متعلقه

-0.43

POSITIVE LOGITS

<bos>

0.62

 NgModule

0.37

Qua

0.31

 dron

0.31

 Drones

0.29

 Beagle

0.29

 Omicron

0.28

BeanFactory

0.28

mir

0.28

 giá

0.28

Activations Density 0.136%

a mix of HTML tags, words associated with academic publications, and the word "Created"

code

No Comments

No Known Activations

a mix of HTML tags, words associated with academic publications, and the word "Created"

code

No Comments

No Known Activations