INDEX

Explanations

proper nouns such as names and locations

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

pter

-0.89

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.88

lisher

-0.84

eatures

-0.82

cffff

-0.80

 Seym

-0.79

sburg

-0.78

lain

-0.78

ãĥ¼ãĥĨ

-0.77

imentary

-0.77

POSITIVE LOGITS

Äĩ

1.42

orno

1.31

plom

1.24

Ã¨re

1.20

ota

1.19

ples

1.19

ye

1.19

oti

1.17

qa

1.13

ks

1.12

Activations Density 10.304%

proper nouns such as names and locations

No Comments

No Known Activations