INDEX

Explanations

descriptions or definitions of historical events or concepts

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

ï¿½ï¿½ï¿½ï¿½

-0.52

Ò

-0.52

thood

-0.51

.</

-0.50

ceive

-0.50

 without

-0.48

poke

-0.47

SPONSORED

-0.47

/"

-0.47

rade

-0.46

POSITIVE LOGITS

oret

1.25

resa

0.96

odore

0.89

ories

0.88

 simplest

0.87

 latter

0.86

 downside

0.85

 easiest

0.81

 biggest

0.81

nce

0.80

Activations Density 13.989%

descriptions or definitions of historical events or concepts

No Comments

No Known Activations

descriptions or definitions of historical events or concepts

No Comments

No Known Activations