INDEX

Explanations

proper nouns, likely names of characters in a story

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

natureconservancy

-0.73

Else

-0.72

uberty

-0.66

stem

-0.63

wcsstore

-0.61

IRO

-0.60

Kin

-0.60

BIT

-0.59

 wrench

-0.59

LV

-0.59

POSITIVE LOGITS

ess

1.18

enance

1.17

esses

1.07

ies

1.03

ries

1.01

ing

0.92

ships

0.86

sburg

0.84

hips

0.84

Activations Density 5.627%

proper nouns, likely names of characters in a story

No Comments

No Known Activations