INDEX

Explanations

proper nouns and specific names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elist

-0.49

opol

-0.47

arb

-0.46

worldly

-0.46

chron

-0.46

Phi

-0.44

 unpre

-0.42

quel

-0.41

mint

-0.41

Unt

-0.40

POSITIVE LOGITS

iard

0.66

sburgh

0.61

sburg

0.59

espie

0.53

enium

0.51

ingham

0.51

bury

0.49

IONS

0.48

uminati

0.48

iflower

0.47

Activations Density 7.986%

proper nouns and specific names

No Comments

No Known Activations