INDEX

Explanations

technical terminology and references related to computer science and programming

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

<bos>

-0.63

исленность

-0.62

 мәкал

-0.58

copus

-0.58

 agujas

-0.56

เอง

-0.55

ricist

-0.54

.”

-0.53

”

-0.52

 mapStateToProps

-0.52

POSITIVE LOGITS

 Besøkt

0.60

脚注の使い方

0.55

MENAFN

0.53

 للمعارف

0.52

nestjs

0.52

ImageContext

0.51

mybatisplus

0.50

原始内容存档于

0.49

isem

0.49

ziała

0.49

Activations Density 0.064%

technical terminology and references related to computer science and programming

No Comments

No Known Activations