INDEX

Explanations

mentions of criminal offenses, including laws and legal actions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

achev

-0.75

quickShipAvailable

-0.73

soDeliveryDate

-0.72

atari

-0.71

mop

-0.68

por

-0.67

visors

-0.67

flush

-0.67

changes

-0.64

ardy

-0.64

POSITIVE LOGITS

 punishable

1.52

 committed

1.19

 offences

1.08

 perpetrated

1.04

 spree

0.99

 crimes

0.95

 convictions

0.95

 offenses

0.94

 misdem

0.93

 conviction

0.92

Activations Density 0.059%

mentions of criminal offenses, including laws and legal actions

No Comments

No Known Activations