INDEX

Explanations

scientific citations and references

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

rete

-0.76

reet

-0.74

 Fiorina

-0.68

mine

-0.68

ndra

-0.66

ulia

-0.65

ROM

-0.65

 Tart

-0.65

RANT

-0.63

atri

-0.62

POSITIVE LOGITS

doi

1.60

://

1.02

DOI

1.01

doi

0.98

ĸļ

0.98

Â¯Â¯Â¯Â¯

0.90

romeda

0.89

hedral

0.85

osphere

0.81

velop

0.80

Activations Density 6.117%

scientific citations and references

No Comments

No Known Activations