INDEX

Explanations

terms related to processes and interactions that indicate action or movement within a system

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoField

-0.44

XmlRootElement

-0.41

AddHtmlAttribute

-0.39

lei

-0.38

期刊论文

-0.35

 surla

-0.35

ConverterFactory

-0.34

blich

-0.33

esModule

-0.32

CreateModel

-0.32

POSITIVE LOGITS

webElementXpaths

0.56

 transfieras

0.55

 estekak

0.54

 चीज़ों

0.52

QMetaType

0.52

optionalTypeArgs

0.52

 OMITBAD

0.50

PARATUS

0.50

 Inſ

0.50

resave

0.49

Activations Density 0.073%

terms related to processes and interactions that indicate action or movement within a system

No Comments

No Known Activations