INDEX

Explanations

references to a specific company and its affiliates

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 VICE

-0.83

urnal

-0.82

 inevitable

-0.80

ossession

-0.80

apa

-0.79

usalem

-0.78

ULTS

-0.78

Downloadha

-0.77

apist

-0.77

FINEST

-0.77

POSITIVE LOGITS

ularity

1.45

eering

1.38

leton

1.32

ling

1.31

ular

1.30

lest

1.28

lers

1.27

leness

1.25

les

1.18

led

1.16

Activations Density 1.030%

references to a specific company and its affiliates

No Comments

No Known Activations