INDEX

Explanations

positive descriptions and attributes related to a community or place

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

kees

-0.91

ï¸

-0.76

çļ

-0.75

eus

-0.74

utterstock

-0.74

obia

-0.73

izon

-0.73

terday

-0.73

theless

-0.73

è£ħ

-0.72

POSITIVE LOGITS

 albeit

1.24

huh

1.05

um

1.00

uh

0.96

 respectively

0.85

 supra

0.84

 though

0.83

 however

0.79

 inclusive

0.78

etc

0.78

Activations Density 2.345%

positive descriptions and attributes related to a community or place

No Comments

No Known Activations