INDEX

Explanations

mentions of law enforcement activities and crime scenes

oai_token-act-pair · gpt-3.5-turbo

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

 veto

-0.74

dream

-0.71

 sins

-0.70

 hypocritical

-0.67

fab

-0.65

Quantity

-0.64

 plagiar

-0.63

 autobi

-0.62

 nipples

-0.62

puff

-0.61

POSITIVE LOGITS

Officers

1.25

 paramedics

1.13

 officers

1.12

 forensic

1.07

illance

1.06

 detectives

1.06

 Officers

1.05

nsics

1.05

 SWAT

1.04

 police

1.04

Activations Density 0.430%

mentions of law enforcement activities and crime scenes

No Comments

No Known Activations