INDEX

Explanations

technical instructions or code snippets

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

adelphia

-0.75

 Hawaiian

-0.72

hab

-0.72

eer

-0.70

 hiber

-0.69

indal

-0.69

haw

-0.68

nesota

-0.67

 camping

-0.66

 Jarrett

-0.66

POSITIVE LOGITS

1.34

1.08

1.01

0.87

0.84

ania

0.82

 Â½

0.81

0.80

ãĤ¹

0.79

Cover

0.76

Activations Density 14.435%

technical instructions or code snippets

No Comments

No Known Activations