INDEX

Explanations

specific keywords related to user authentication processes

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

AddTagHelper

-0.54

apimachinery

-0.52

 تضيفلها

-0.48

 Infórmanos

-0.47

ఔ

-0.46

 linkovi

-0.45

 ujednoznacz

-0.43

SourceChecksum

-0.43

setVerticalGroup

-0.41

 createSprite

-0.41

POSITIVE LOGITS

 asking

0.55

 Asking

0.50

Questionnaire

0.48

 questionnaire

0.48

uș

0.47

 kér

0.47

 soliciting

0.46

 micrófono

0.46

Asking

0.46

 Questionnaire

0.45

Activations Density 0.432%

specific keywords related to user authentication processes

No Comments

No Known Activations