INDEX

Explanations

references to legal acts and regulations

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

"Act" followed by legal or procedural terms

np_acts-logits-general · gemini-2.0-flash

names of acts and laws

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 يتيمه

-0.56

parsedMessage

-0.53

InstrumentedTest

-0.52

 Grüsse

-0.50

}{@

-0.49

TagHelper

-0.47

UseVisualStyle

-0.47

tranno

-0.45

 virtuel

-0.45

 Empfindung

-0.45

POSITIVE LOGITS

law

0.70

 statutes

0.63

 laws

0.63

 statute

0.61

 Statute

0.58

Law

0.57

 zák

0.56

 Statutes

0.56

Act

0.51

 legislation

0.51

Activations Density 0.919%

references to legal acts and regulations

"Act" followed by legal or procedural terms

names of acts and laws

No Comments

No Known Activations