INDEX

Explanations

references to law enforcement agencies

oai_token-act-pair · gpt-3.5-turbo

mentions of sheriff offices and their associated activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

lihood

-0.79

 deaf

-0.71

jad

-0.71

PsyNetMessage

-0.68

FORE

-0.67

yip

-0.67

piring

-0.67

figure

-0.65

 Shutterstock

-0.65

ilater

-0.65

POSITIVE LOGITS

 Sheriff

1.10

 Marshal

0.98

 Supervisor

0.83

osate

0.81

 sheriff

0.78

 Enforcement

0.78

 Superintendent

0.77

 Commissioner

0.77

 Clerk

0.75

 Prosecutor

0.75

Activations Density 0.013%

references to law enforcement agencies

mentions of sheriff offices and their associated activities

No Comments

No Known Activations