INDEX

Explanations

life events and personal details described in narrative text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enko

-0.31

eni

-0.26

imar

-0.26

 Hort

-0.25

ped

-0.25

uner

-0.24

Dek

-0.23

elist

-0.23

anda

-0.23

utra

-0.23

POSITIVE LOGITS

 ILCS

0.24

 misunder

0.24

holes

0.23

 masc

0.23

ops

0.22

 inequalities

0.22

services

0.22

 lineback

0.22

 loopholes

0.22

ridges

0.22

Activations Density 0.022%

life events and personal details described in narrative text

No Comments

No Known Activations