INDEX

Explanations

scientific and technical terminology related to laboratory procedures and experiments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

humans

-0.34

sheets

-0.28

rooms

-0.27

tal

-0.27

aments

-0.27

profits

-0.27

ework

-0.26

pees

-0.26

 accommodations

-0.26

hur

-0.25

POSITIVE LOGITS

 separately

0.36

 statically

0.31

byss

0.30

Obj

0.29

 manually

0.28

 anew

0.28

 mechanically

0.27

 psychiat

0.27

 withd

0.27

 altern

0.27

Activations Density 6.625%

scientific and technical terminology related to laboratory procedures and experiments

No Comments

No Known Activations