INDEX

Explanations

words and phrases associated with academic papers, research, and studies

oai_token-act-pair · gemini-2.0-flash

programming-related terms

np_token-act-pair-logits · gpt-4o-mini

and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

imageshack

-0.54

 melanin

-0.51

 purpoſe

-0.50

 MongoClient

-0.50

writeValue

-0.50

starch

-0.50

 ransomware

-0.50

 laſt

-0.49

Према

-0.48

AndView

-0.47

POSITIVE LOGITS

tvguidetime

0.68

its

0.66

WriteBarrier

0.63

 AttributeSet

0.62

ValueStyle

0.60

WireFormat

0.56

 kasarigan

0.56

 OnInit

0.55

retti

0.54

complexType

0.53

Activations Density 3.557%

words and phrases associated with academic papers, research, and studies

programming-related terms

and

No Comments

No Known Activations