INDEX

Explanations

references to crime and law enforcement

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NOPQRST

-0.61

UrlResolution

-0.59

atisfaction

-0.55

 المعيارى

-0.55

esgue

-0.54

mallows

-0.54

ImageField

-0.53

atihan

-0.52

mbggenerated

-0.52

Спасылкі

-0.51

POSITIVE LOGITS

 gangster

0.77

GTA

0.73

 gang

0.73

 gangsters

0.72

 heist

0.65

GTA

0.65

 robbery

0.65

 Rockstar

0.63

 robbing

0.62

Gang

0.60

Activations Density 0.179%

references to crime and law enforcement

No Comments

No Known Activations