INDEX

Explanations

sentences discussing issues related to truth, credibility, and the gap between reality and perception

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

cair

-0.79

indal

-0.77

artney

-0.73

asus

-0.73

asso

-0.72

edo

-0.67

rosse

-0.67

oyal

-0.67

ucky

-0.65

incinn

-0.65

POSITIVE LOGITS

istically

0.91

ignment

0.86

psons

0.79

 reality

0.79

reality

0.74

fulness

0.71

Wiz

0.68

 distortion

0.68

 Reborn

0.65

isation

0.65

Activations Density 10.508%

sentences discussing issues related to truth, credibility, and the gap between reality and perception

No Comments

No Known Activations