INDEX

Explanations

C code related to PCI configuration

oai_token-act-pair · gemini-2.0-flash

specific programming or technical terms

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

Code data structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddHtmlAttribute

-0.76

 wireType

-0.75

exitRule

-0.72

 Италијани

-0.71

matchCondition

-0.68

 tartalomajánló

-0.65

featureID

-0.64

IndentedString

-0.64

writeField

-0.62

 ویکی‌پدیا

-0.60

POSITIVE LOGITS

RectangleBorder

0.49

fohlen

0.46

saraba

0.46

ylar

0.43

 digitalen

0.41

ințe

0.41

GraphicsUnit

0.41

 presença

0.41

 compreensão

0.41

gebnisse

0.40

Activations Density 1.567%

C code related to PCI configuration

specific programming or technical terms

Code data structures

No Comments

No Known Activations