INDEX

Explanations

technical terms and specific metrics related to engineering and semiconductor design

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

 gafas

-0.35

 alvor

-0.32

 entendido

-0.32

 cumplido

-0.31

 razonable

-0.29

 gröss

-0.29

 enamorado

-0.29

 zwey

-0.29

 desconocido

-0.29

 vuestro

-0.28

POSITIVE LOGITS

 صوتيه

0.78

########.

0.77

DispatchToProps

0.76

verwijspagina

0.75

MessageOf

0.75

下载附件

0.73

 שוליים

0.73

Datuak

0.73

 informée

0.73

protoimpl

0.73

Activations Density 1.586%

technical terms and specific metrics related to engineering and semiconductor design

No Comments

No Known Activations