INDEX

Explanations

references to violent actions and physical aggression

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

Acts of violence/aggression

np_acts-logits-general · gemini-2.0-flash

physical attacks and injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

脚注の使い方

-0.64

 препратки

-0.61

出版年

-0.59

IonicModule

-0.58

homonymie

-0.57

énario

-0.56

IVEREF

-0.54

DockStyle

-0.54

METHOD

-0.53

 insuffisamment

-0.51

POSITIVE LOGITS

ReusableCell

0.57

 HttpNotFound

0.56

ControllerAdvice

0.53

 head

0.53

ductor

0.52

!*\

0.51

runApp

0.50

 touristique

0.49

duras

0.49

 skrevet

0.49

Activations Density 0.100%

references to violent actions and physical aggression

Acts of violence/aggression

physical attacks and injuries

No Comments

No Known Activations