INDEX

Explanations

concluding phrases or statements in a text

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

elled

-1.17

prus

-1.14

Tai

-1.06

ells

-1.04

 Siber

-0.97

Lat

-0.97

existent

-0.95

Americ

-0.95

cat

-0.94

pins

-0.93

POSITIVE LOGITS

 aside

1.27

 though

1.07

 hindsight

1.01

 caveats

0.99

 however

0.98

lihood

0.98

 caveat

0.97

herty

0.94

ity

0.93

nostic

0.92

Activations Density 0.514%

concluding phrases or statements in a text

No Comments

No Known Activations