INDEX

Explanations

terms related to biometric authentication and security methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.91

########.

-0.70

 betweenstory

-0.69

 Bandcamp

-0.58

DeleteBehavior

-0.57

yntaxException

-0.55

AndEndTag

-0.55

 corpus

-0.53

 coar

-0.53

igslist

-0.52

POSITIVE LOGITS

bio

1.18

 biometric

1.06

bio

0.98

Bio

0.95

 fingerprint

0.91

ID

0.86

Bio

0.85

 identity

0.83

 identification

0.81

 finger

0.80

Activations Density 0.274%

terms related to biometric authentication and security methods

No Comments

No Known Activations