INDEX

Explanations

violent or aggressive behavior, conflict, and negative interactions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITNESS

-0.72

mberg

-0.67

ourced

-0.64

avez

-0.64

inoa

-0.64

ucket

-0.61

ovember

-0.61

ĸļ

-0.61

agine

-0.60

PsyNetMessage

-0.60

POSITIVE LOGITS

ly

1.06

ness

0.74

nesses

0.73

icious

0.70

 circle

0.67

 vicious

0.64

 assault

0.60

 havoc

0.59

 retribution

0.59

 bite

0.59

Activations Density 10.914%

violent or aggressive behavior, conflict, and negative interactions

No Comments

No Known Activations