INDEX

Explanations

evidence and references related to legal proceedings or rulings

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

followed by actions or applications

np_acts-logits-general · gemini-2.0-flash

legal and technical processes

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



-0.51

 surla

-0.50

extAlignment

-0.46

 fortæ

-0.43

ClientRect

-0.40

 Вікіпе

-0.39

-0.38

 rhestr

-0.36

舺

-0.35

wpi

-0.35

POSITIVE LOGITS

 ویکی‌پدی

0.92

 noDo

0.81

ьаж

0.77

IUrlHelper

0.77

msgTypes

0.71

IndentedString

0.68

ंदीखरीदारी

0.67

Personensuche

0.66

AutoScaleMode

0.66

 NSCoder

0.66

Activations Density 32.184%

evidence and references related to legal proceedings or rulings

followed by actions or applications

legal and technical processes

No Comments

No Known Activations