INDEX

Explanations

references to legal acts or regulations

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

tsky

-1.07

ovych

-0.92

pocket

-0.89

sbm

-0.88

ths

-0.87

hiba

-0.87

cash

-0.87

anyl

-0.85

oyal

-0.85

 unin

-0.85

POSITIVE LOGITS

uary

1.42

ional

1.30

 Amendments

1.23

Thumbnail

1.18

Fram

1.15

breakers

1.06

breaker

1.04

iard

1.02

acebook

1.01

ors

1.00

Activations Density 0.577%

references to legal acts or regulations

No Comments

No Known Activations