INDEX

Explanations

the abbreviation "PLOS" and terms related to rendering in programming

oai_token-act-pair · gemini-2.0-flash

los

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalTable

-0.53

 HttpNotFound

-0.51

 missing

-0.50

ьаж

-0.48

Carriera

-0.48

 Saltar

-0.47

PageFactory

-0.47

igshid

-0.47

Missing

-0.47

 beginnetje

-0.47

POSITIVE LOGITS

 كومونز

0.61

esez

0.59

PostInfinity

0.57

 Alat

0.55

rium

0.53

 resourceCulture

0.52

isNameExpr

0.52

VHS

0.52

perg

0.52

etus

0.52

Activations Density 0.437%

the abbreviation "PLOS" and terms related to rendering in programming

los

No Comments

No Known Activations