INDEX

Explanations

phrases related to usernames and passwords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 CreateTagHelper

-0.56

TagHelper

-0.53

defer

-0.51

ধ্য

-0.49

 formales

-0.49

zellan

-0.49

 professionali

-0.49

üyor

-0.49

رشف

-0.48

XmlRootElement

-0.48

POSITIVE LOGITS

 Password

1.08

 password

1.02

 getPassword

1.01

 PASSWORD

0.99

PasswordEncoder

0.99

Password

0.94

password

0.94

PASSWORD

0.93

 passphrase

0.90

 passwords

0.89

Activations Density 0.167%

phrases related to usernames and passwords

No Comments

No Known Activations