INDEX

Explanations

text related to crime, especially murder cases and criminal activities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cola

-0.75

wcsstore

-0.70

BuyableInstoreAndOnline

-0.68

uve

-0.67

acea

-0.61

ais

-0.60

orers

-0.58

 reusable

-0.57

Gi

-0.57

ertain

-0.57

POSITIVE LOGITS

 spree

1.04

 murder

0.90

 rampage

0.80

ously

0.79

 murders

0.79

 homicide

0.79

hyde

0.75

 murderer

0.75

 victim

0.73

 mysteries

0.73

Activations Density 7.739%

text related to crime, especially murder cases and criminal activities

No Comments

No Known Activations