INDEX

Explanations

Dungeons and Dragons (D&D) game-related content

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

Preview

-0.83

leased

-0.81

etta

-0.79

grab

-0.77

Interstitial

-0.76

agar

-0.73

ï¸

-0.73

dullah

-0.69

deck

-0.69

Pog

-0.69

POSITIVE LOGITS

lor

0.90

hyde

0.90

 Disciple

0.84

alion

0.76

ancy

0.74

uction

0.74

upid

0.73

ulhu

0.72

acies

0.71

cture

0.71

Activations Density 0.110%

Dungeons and Dragons (D&D) game-related content

No Comments

No Known Activations