INDEX

Explanations

phrases related to future time periods

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icone

-1.01

cca

-0.94

lees

-0.91

hes

-0.88

ocker

-0.88

bos

-0.88

theless

-0.86

pas

-0.86

 Feldman

-0.85

lee

-0.85

POSITIVE LOGITS

 installment

1.22

 generation

1.18

 step

1.15

 iteration

1.15

decade

1.14

 crop

1.12

 generations

1.08

 batch

1.06

 gasp

1.05

 phase

1.05

Activations Density 0.351%

phrases related to future time periods

No Comments

No Known Activations