INDEX

Explanations

occurrences of legal and law enforcement terminology related to incidents and arrests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

HandlerContext

-0.60

ewel

-0.58

kháu

-0.54

 سكانية

-0.54

 Sjö

-0.46

 VIAF

-0.45

indd

-0.45

esine

-0.45

 targets

-0.45

摇摇头

-0.44

POSITIVE LOGITS

 Mifflin

0.54

WriteAttribute

0.54

 Swat

0.53

 Landis

0.52

 betweenstory

0.52

AutoScale

0.51

出版年

0.50

 Hummel

0.49

 Friedens

0.49

 Northumberland

0.49

Activations Density 0.227%

occurrences of legal and law enforcement terminology related to incidents and arrests

No Comments

No Known Activations