INDEX

Explanations

keywords and phrases related to legal terms, structures, and official documents

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

Text before function names or code snippets

np_acts-logits-general · gemini-2.0-flash

United States District Court

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

曖昧さ回避

-0.33

 αντί

-0.33

isce

-0.32

pre

-0.32

relativeTime

-0.32

LBL

-0.31

GTCX

-0.31

AsUp

-0.31

 hẳn

-0.30

 роста

-0.30

POSITIVE LOGITS

featureID

0.70

/**

0.69

 kasarigan

0.63

bootstrapcdn

0.55

afficheront

0.53

 متعلقه

0.53

CodeAttribute

0.51

ⓧ

0.50

 Roskov

0.50

LayoutStyle

0.49

Activations Density 1.270%

keywords and phrases related to legal terms, structures, and official documents

Text before function names or code snippets

United States District Court

No Comments

No Known Activations