INDEX

Explanations

pieces of text describing technical details and specifications related to electronic devices

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

•Layer 6 UMAP region: Mixed cluster on right - local

No Comments

Negative Logits

Lens

-0.78

birds

-0.71

vous

-0.68

femin

-0.65

Russ

-0.64

fill

-0.63

FTWARE

-0.62

Ops

-0.61

arch

-0.61

film

-0.61

POSITIVE LOGITS

 least

1.18

abase

1.12

rial

0.93

onement

0.88

 dusk

0.81

rium

0.77

mega

0.77

 variance

0.76

 intervals

0.76

omic

0.76

Activations Density 13.793%

pieces of text describing technical details and specifications related to electronic devices

No Comments

No Known Activations