INDEX

Explanations

programming-related terms and structures within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

脚注の使い方

-0.66

 mentes

-0.64

 gärna

-0.63

RegressionTest

-0.62

تقاوى

-0.61

 الحره

-0.60

qtype

-0.59

Abit

-0.58

ReusableCell

-0.56

LEncoder

-0.55

POSITIVE LOGITS

multer

0.67

SourceChecksum

0.59

 useStyles

0.58

ніципа

0.57

LoggerFactory

0.56

 GenerationType

0.54

 useDispatch

0.54

awtextra

0.53

 rospy

0.53

 useRouter

0.53

Activations Density 0.037%

programming-related terms and structures within code snippets

No Comments

No Known Activations