INDEX

Explanations

occurrences of the word "gh"

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

secut

-0.86

IAL

-0.81

 closest

-0.80

BuyableInstoreAndOnline

-0.79

 Faust

-0.79

 prescribed

-0.78

 kindred

-0.77

 indo

-0.76

 satell

-0.76

 Bots

-0.76

POSITIVE LOGITS

ttp

1.54

ouls

1.33

tml

1.24

orns

1.22

orst

1.20

awk

1.17

orn

1.11

olds

1.10

olics

1.10

arrison

1.09

Activations Density 5.728%

occurrences of the word "gh"

No Comments

No Known Activations