INDEX

Explanations

mentions of bans

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

 Generations

-0.80

 IMAGES

-0.78

lycer

-0.73

 Barg

-0.69

rious

-0.69

 Apostles

-0.67

 Temper

-0.67

Â¯Â¯

-0.66

 Directions

-0.65

Pub

-0.64

POSITIVE LOGITS

ishment

1.30

hammer

1.11

hee

1.04

ishing

0.96

zai

0.92

tering

0.92

ished

0.92

nered

0.91

ish

0.89

eful

0.86

Activations Density 4.290%

mentions of bans

No Comments

No Known Activations