INDEX

Explanations

technical and potentially programming-related terms or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SourceChecksum

-0.52

 BorderSide

-0.48

Abp

-0.45

bootstrapcdn

-0.40

новниш

-0.40

openzeppelin

-0.40

 MonoBehaviour

-0.39

sizePolicy

-0.39

Personensuche

-0.38

classnames

-0.38

POSITIVE LOGITS

 noDo

0.50

 تضيفلها

0.45

PreferredItem

0.44

Ở

0.41

zywa

0.41

adpleegd

0.41

 šķ

0.41

 '\\;'

0.39

 ostro

0.39

ayuno

0.39

Activations Density 0.125%

technical and potentially programming-related terms or codes

No Comments

No Known Activations