INDEX

Explanations

social media platforms

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

Negative Logits

nces

-1.33

ved

-1.07

ptin

-1.02

inence

-1.00

teen

-0.97

cephal

-0.97

 Croat

-0.97

zin

-0.97

ration

-0.95

toe

-0.95

POSITIVE LOGITS

 Messenger

1.47

nect

1.31

username

1.22

icus

1.07

ileaks

1.05

 Live

1.04

Friends

1.04

 Timeline

1.03

 Likes

1.03

Money

1.03

Activations Density 0.653%

social media platforms

No Known Activations