INDEX

Explanations

file names, sizes, and software versions

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

omorph

-0.28

actory

-0.24

inally

-0.23

idity

-0.23

udeb

-0.22

iness

-0.22

oping

-0.22

atively

-0.22

ional

-0.21

opathic

-0.21

POSITIVE LOGITS

VP

0.25

NetMessage

0.25

PS

0.24

HK

0.24

PG

0.23

DEBUG

0.23

ACH

0.22

UGE

0.22

/-

0.22

+.

0.22

Activations Density 16.648%

file names, sizes, and software versions

No Comments

No Known Activations