INDEX

Explanations

the mention of specific measurements and data related to scientific experiments

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

 reckoning

-0.73

urer

-0.70

izzy

-0.70

 footing

-0.70

 behav

-0.70

 comparative

-0.70

eling

-0.69

nosis

-0.68

 correspondence

-0.67

 histories

-0.67

POSITIVE LOGITS

MSN

1.13

=-=-

0.85

APTER

0.83

phot

0.82

0.78

LINE

0.78

éĹĺ

0.77

PsyNetMessage

0.76

deg

0.76

Activations Density 20.709%

the mention of specific measurements and data related to scientific experiments

No Comments

No Known Activations