INDEX

Explanations

terms associated with legal actions and criminal proceedings, particularly focusing on arrests and warrants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CYTHON

-0.70

SiO

-0.66

Ge

-0.65

ge

-0.63

migrationBuilder

-0.60

 AutoMapper

-0.60

ipedia

-0.59

termilk

-0.59

 Trip

-0.59

icator

-0.59

POSITIVE LOGITS

 arrest

2.15

 arrested

2.04

 arrests

2.02

 Arrest

2.02

arrest

1.85

Arrest

1.81

 arresting

1.68

 Arrested

1.61

逮捕

1.18

 arrêté

1.05

Activations Density 0.103%

terms associated with legal actions and criminal proceedings, particularly focusing on arrests and warrants

No Comments

No Known Activations