INDEX

Explanations

references to applications and their related functionalities or contexts

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

"application"

np_acts-logits-general · gemini-2.0-flash

application and applications

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

StructEnd

-0.61

 Numerade

-0.57

 tunggu

-0.55

nõ

-0.52

 Überblick

-0.49

 ética

-0.49

(!_

-0.49

oneofs

-0.48

 sağlar

-0.48

 zuletzt

-0.47

POSITIVE LOGITS

 application

1.22

Application

1.20

 Application

1.16

application

1.15

getApplication

1.00

 APPLICATION

0.95

 applications

0.92

 getApplication

0.91

APPLICATION

0.90

 applic

0.89

Activations Density 0.040%

references to applications and their related functionalities or contexts

"application"

application and applications

No Comments

No Known Activations