INDEX

Explanations

terms related to usernames and credentials in code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-1.10

 AssemblyCulture

-1.09

MLLoader

-0.97

 ModelExpression

-0.95

reportWebVitals

-0.93

Odkazy

-0.93

__":

-0.86

 trajets

-0.83

 ProgressDialog

-0.82

="@+

-0.81

POSITIVE LOGITS

username

1.54

 username

1.51

Username

1.48

getUsername

1.43

setUsername

1.38

 getUsername

1.31

 setUsername

1.28

 Username

1.26

USERNAME

1.10

 usernames

1.08

Activations Density 0.115%

terms related to usernames and credentials in code

No Comments

No Known Activations