INDEX

Explanations

technical terms related to computer systems and procedures

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

lich

-0.16

ASED

-0.15

ãĥĥ

-0.15

¾

-0.15

lord

-0.14

 pest

-0.14

wheel

-0.14

ãĥĥãĤ¯

-0.14

neck

-0.14

poll

-0.13

POSITIVE LOGITS

kaya

0.23

oft

0.21

 Seeking

0.20

hire

0.19

hift

0.19

layer

0.19

cript

0.18

 Ways

0.18

ky

0.17

":["

0.17

Activations Density 5.890%

technical terms related to computer systems and procedures

No Comments

No Known Activations