INDEX

Explanations

terms related to law enforcement and police activity

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

law enforcement personnel and actions

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 kasarigan

-0.73

+#+#

-0.72

 queſta

-0.71

 noDo

-0.69

 Италијани

-0.67

хьтан

-0.67

'{@

-0.66

KURZBESCHREIBUNG

-0.66

:✨

-0.65

⅘

-0.65

POSITIVE LOGITS

 שוליים

0.42

 patrulla

0.35

 immediately

0.35

 quickly

0.34

 police

0.31

 patrol

0.29

cop

0.29

 swiftly

0.29

 Police

0.28

try

0.28

Activations Density 0.005%

terms related to law enforcement and police activity

law enforcement personnel and actions

No Comments

No Known Activations