INDEX

Explanations

references to the police or 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

rungsseite

-0.87

windowFixed

-0.81

 Giver

-0.79

 AssemblyVersion

-0.73

ReusableCell

-0.69

 Sinks

-0.68

 beginnetje

-0.67

EndContext

-0.66

 AssemblyTitle

-0.65

UnsafeEnabled

-0.65

POSITIVE LOGITS

 police

3.10

 Police

2.85

Police

2.78

police

2.78

 POLICE

2.60

 policemen

2.00

警察

1.90

 policía

1.87

 policeman

1.86

 Polizei

1.82

Activations Density 0.065%

references to the police or law enforcement

No Comments

No Known Activations