INDEX

Explanations

references to governmental and legal contexts, particularly involving the Patriot Act and related discussions

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

9/11 and terrorism

np_acts-logits-general · gemini-2.0-flash

9/11 attacks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Chwiliwch

-0.68

ⓧ

-0.67

 AttributeSet

-0.65

 autorytatywna

-0.64

queryInterface

-0.64

 дописавши

-0.63

脚注の使い方

-0.63

 propOrder

-0.61

 chi̍t

-0.60

 دیکھیے

-0.60

POSITIVE LOGITS

 attacks

0.86

 terrorist

0.86

 Sept

0.85

 September

0.79

 attack

0.77

 terrorists

0.76

 Attacks

0.75

 terrorism

0.75

 Terror

0.72

 ataques

0.71

Activations Density 0.134%

references to governmental and legal contexts, particularly involving the Patriot Act and related discussions

9/11 and terrorism

9/11 attacks

No Comments

No Known Activations