INDEX

Explanations

references to physical interactions such as shaking hands and laying hands on in various contexts

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

nea

-0.27

pent

-0.27

central

-0.27

nit

-0.26

empt

-0.25

cyclop

-0.24

gotten

-0.24

elin

-0.24

mental

-0.23

 Midlands

-0.23

POSITIVE LOGITS

 greet

0.27

atform

0.24

 greets

0.24

 afar

0.24

aires

0.23

ospons

0.23

Dialogue

0.23

bernatorial

0.23

 attendees

0.22

 passers

0.22

Activations Density 11.667%

references to physical interactions such as shaking hands and laying hands on in various contexts

No Comments

No Known Activations