INDEX

Explanations

LaTeX code related to figures and documents

oai_token-act-pair · gemini-2.0-flash

document formatting

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

webElementXpaths

-1.16

RegressionTest

-0.99

oredCriteria

-0.97

DeleteBehavior

-0.92

WebElementEntity

-0.92

 nahilalakip

-0.91

ClientSize

-0.87

ⓧ

-0.85

 cherchés

-0.84

 Италијани

-0.82

POSITIVE LOGITS

+:+

0.54

代

0.47

forderung

0.47

 Armed

0.47

inosaur

0.46

oc

0.46

 Polytechnic

0.46

ung

0.45

un

0.44

bonucleic

0.44

Activations Density 25.496%

LaTeX code related to figures and documents

document formatting

No Comments

No Known Activations