INDEX

Explanations

structured data definitions and their properties in code, particularly focusing on types and nullable attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

errHandler

-0.69

ViewFeatures

-0.69

 IconData

-0.66

 بيها

-0.65

 estekak

-0.65

reportWebVitals

-0.63

(!__

-0.60

StoryboardSegue

-0.59

 OMITBAD

-0.58

nesc

-0.58

POSITIVE LOGITS

 فريبيس

0.46

letor

0.40

Descrição

0.40

Riverside

0.40

 mahar

0.40

aso

0.40

ubon

0.40

mschrijving

0.39

WebServlet

0.39

 Gaulle

0.39

Activations Density 0.062%

structured data definitions and their properties in code, particularly focusing on types and nullable attributes

No Comments

No Known Activations