INDEX

Explanations

names of persons or organizations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

•Layer 6 UMAP region: Mostly-local cluster on left - e2e-recon

No Comments

Negative Logits

FIG

-0.90

assium

-0.88

eral

-0.88

ivia

-0.83

ginx

-0.82

abilia

-0.82

cens

-0.81

lated

-0.80

illed

-0.80

itars

-0.79

POSITIVE LOGITS

 virtue

1.23

laws

0.99

products

0.99

 leaps

0.94

 announcing

0.92

 signing

0.87

 allowing

0.87

 default

0.86

 adding

0.85

Activations Density 1.347%

names of persons or organizations

No Comments

No Known Activations