INDEX

Explanations

code-related terms and phrases associated with high-performance computing and GPU specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Diwedd

-0.72

ंदीखरीदारी

-0.65

ItemBackground

-0.57

ViewImports

-0.56

 propOrder

-0.54

 metaphysical

-0.53

 Vary

-0.52

codable

-0.52

ciaż

-0.51

irus

-0.50

POSITIVE LOGITS

 whoever

0.81

 Whoever

0.75

Whoever

0.73

ConstraintMaker

0.69

Hentet

0.64

who

0.62

 whome

0.60

StoryboardSegue

0.60

الإنجليزية

0.57

 ProtoMessage

0.56

Activations Density 0.191%

code-related terms and phrases associated with high-performance computing and GPU specifications

No Comments

No Known Activations