INDEX

Explanations

specific character names and terms from a fictional universe or game

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

تقاوى

-0.73

 useAppContext

-0.65

 estekak

-0.63

ProgressHUD

-0.61

TagMode

-0.57

izzera

-0.55

afficheront

-0.53

 passagers

-0.53

المناصب

-0.53

BufferException

-0.53

POSITIVE LOGITS

etc

0.65

etc

0.65

PageIndex

0.53

manos

0.53

Efq

0.52

ised

0.50

osv

0.50

respectively

0.49

oredCriteria

0.47

 неё

0.47

Activations Density 0.159%

specific character names and terms from a fictional universe or game

No Comments

No Known Activations