INDEX

Explanations

scenarios involving alternate timelines, parallel universes, and manipulation of physical reality

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

okes

-0.73

evin

-0.72

 acknowled

-0.68

iferation

-0.66

ovember

-0.61

arkin

-0.61

 inquiries

-0.60

anton

-0.60

ong

-0.60

enary

-0.60

POSITIVE LOGITS

 scenario

0.85

 conditions

0.80

 predetermined

0.77

essim

0.72

0.71

mx

0.70

 Wilderness

0.69

layout

0.68

 scenarios

0.68

 equilibrium

0.68

Activations Density 18.345%

scenarios involving alternate timelines, parallel universes, and manipulation of physical reality

No Comments

No Known Activations