INDEX

Explanations

words relating to organizations and companies, with some bias towards technology and government

oai_token-act-pair · 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

цездатний

-0.56

Personendaten

-0.55

 judiciaire

-0.54

 consultato

-0.53

cyjny

-0.52

acyjny

-0.52

'<?

-0.50

Aggregator

-0.50

Tembelea

-0.49

 compte

-0.49

POSITIVE LOGITS

BagLayout

0.82

AndEndTag

0.63

RectangleBorder

0.63

 defaultstate

0.60

WriteAttribute

0.59

 EconPapers

0.58

UnusedPrivate

0.57

oneofs

0.51

viewDidLoad

0.51

WriteTagHelper

0.50

Activations Density 0.709%

words relating to organizations and companies, with some bias towards technology and government

No Comments

No Known Activations