INDEX

Explanations

instances of the word "for" when it describes a beneficial outcome

oai_token-act-pair · gemini-2.0-flash

Product features and benefits

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCompany

-0.80

 وتسجيلات

-0.77

 saites

-0.71

rophes

-0.63

MigrationBuilder

-0.62

GIVEREF

-0.61

zeera

-0.61

IndentedString

-0.60

曖昧さ回避

-0.60

Cubit

-0.57

POSITIVE LOGITS

<?

0.53

 ostavi

0.50

 longer

0.49

Longer

0.48

cektir

0.47

lawless

0.46

 ""],

0.45

 maximum

0.45

ters

0.45

 optimum

0.44

Activations Density 1.971%

instances of the word "for" when it describes a beneficial outcome

Product features and benefits

No Comments

No Known Activations