INDEX

Explanations

references to time periods, particularly historical eras and centuries

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

hod

-1.30

iquid

-1.25

atem

-1.21

etsk

-1.17

agged

-1.15

govtrack

-1.13

ippi

-1.07

imov

-1.07

Downloadha

-1.05

yang

-1.05

POSITIVE LOGITS

 onwards

1.15

 onward

1.10

 hindsight

1.06

BCE

1.04

 Revival

1.00

 Inquisition

0.99

 Circus

0.97

 Heritage

0.95

 Typhoon

0.95

 Clicker

0.93

Activations Density 0.690%

references to time periods, particularly historical eras and centuries

No Comments

No Known Activations