INDEX

Explanations

phrases related to exercises and active learning opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 legale

-0.50

 aéreo

-0.48

 discorso

-0.46

 tapering

-0.44

 viewDidLoad

-0.44

UrlResolution

-0.43

ason

-0.42

道理

-0.42

Ri

-0.41

 erschien

-0.41

POSITIVE LOGITS

الحياه

0.82

DeleteBehavior

0.72

出版年

0.71

migrationBuilder

0.68

 interactive

0.65

EXERC

0.64

 <=",

0.64

endphp

0.62

ArgsConstructor

0.61

 мәкал

0.60

Activations Density 0.341%

phrases related to exercises and active learning opportunities

No Comments

No Known Activations