INDEX

Explanations

vocabulary related to morality and morals

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

xual

-1.18

rams

-1.11

essions

-1.10

lers

-1.09

 Pavilion

-1.06

hips

-1.04

kt

-1.00

WER

-1.00

hw

-1.00

gow

-0.99

POSITIVE LOGITS

 hazard

1.41

 compass

1.38

istic

1.36

istically

1.29

 equival

1.24

ising

1.23

 conscience

1.21

 indignation

1.21

 dile

1.18

ised

1.17

Activations Density 1.139%

vocabulary related to morality and morals

No Comments

No Known Activations