INDEX

Explanations

mentions of known personalities, especially in a professional or competitive context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.74

¥ŀ

-0.65

ortmund

-0.65

earchers

-0.64

urat

-0.62

andel

-0.61

ãĥ¼ãĥ³

-0.59

ugar

-0.59

 Pradesh

-0.59

avers

-0.58

POSITIVE LOGITS

ess

1.03

who

1.00

esses

0.97

hood

0.93

 extraord

0.89

 whom

0.88

who

0.86

ship

0.83

hunt

0.83

stown

0.82

Activations Density 3.134%

mentions of known personalities, especially in a professional or competitive context

No Comments

No Known Activations

mentions of known personalities, especially in a professional or competitive context

No Comments

No Known Activations