INDEX

Explanations

terms associated with data manipulation and array operations in programming

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

sitis

-0.53

–

-0.51

til

-0.49

Fly

-0.49

 till

-0.49

 Land

-0.49

 Hill

-0.48

-0.46

лан

-0.46

POSITIVE LOGITS

 referenties

0.82

 Majefty

0.74

 ſmall

0.73

InputBorder

0.71

Zeneca

0.71

 tuong

0.71

 Houſe

0.71

 télécommande

0.67

 ――――――――

0.67

 ModelExpression

0.66

Activations Density 0.258%

terms associated with data manipulation and array operations in programming

No Comments

No Known Activations