INDEX

Explanations

terms and concepts related to logistics, infrastructure, and technology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

conn

-0.15

 rooting

-0.15

 TAMADRA

-0.14

 DRAGON

-0.13

fur

-0.13

 Chattanooga

-0.13

 Vine

-0.13

 Flesh

-0.13

 nude

-0.13

ocal

-0.13

POSITIVE LOGITS

opher

0.17

istics

0.16

 Oper

0.16

mith

0.16

ians

0.15

ophers

0.15

tarian

0.15

Engineers

0.15

 Satellite

0.14

Tokens

0.14

Activations Density 21.026%

terms and concepts related to logistics, infrastructure, and technology

No Comments

No Known Activations