INDEX

Explanations

mentions and references to online platforms, political figures, and news events

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

renheit

-0.79

 attribution

-0.66

 Quit

-0.64

DERR

-0.64

 Kinnikuman

-0.64

 neutrality

-0.62

 cessation

-0.62

èª

-0.61

oise

-0.59

OPLE

-0.59

POSITIVE LOGITS

omething

1.46

pace

1.11

hots

1.11

ql

0.97

functional

0.95

cape

0.92

hare

0.90

oteric

0.90

leep

0.89

ullivan

0.88

Activations Density 8.435%

mentions and references to online platforms, political figures, and news events

No Comments

No Known Activations