INDEX

Explanations

words related to law enforcement and policing

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement and policing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isted

-0.85

xual

-0.83

 Remastered

-0.79

yip

-0.78

ļéĨĴ

-0.77

igible

-0.73

ebted

-0.73

opian

-0.71

 Daylight

-0.69

vironment

-0.69

POSITIVE LOGITS

 officers

1.28

 departments

1.26

 officer

1.17

 brutality

1.16

 department

1.10

 chiefs

1.07

 Officers

1.05

 academy

1.05

 acad

1.02

 commissioner

1.00

Activations Density 0.084%

words related to law enforcement and policing

references to law enforcement and policing

No Comments

No Known Activations