INDEX

Explanations

terms related to biometric identification, particularly fingerprints and their various forms

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

"fingerprints"

np_acts-logits-general · gemini-2.0-flash

fingerprints and signatures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 pomeriggio

-0.33

 However

-0.30

periodo

-0.28

 settore

-0.28

But

-0.28

 Konkurrenz

-0.27

 yanında

-0.27

hébergement

-0.27

uttavia

-0.26

 proposed

-0.26

POSITIVE LOGITS

 fingerprint

1.66

fingerprint

1.63

 Fingerprint

1.53

 fingerprints

1.48

Fingerprint

1.38

 signature

1.16

signature

1.12

 footprints

1.09

 SIGNATURE

1.09

 footprint

1.08

Activations Density 0.375%

terms related to biometric identification, particularly fingerprints and their various forms

"fingerprints"

fingerprints and signatures

No Comments

No Known Activations