INDEX

Explanations

contact information related to a product recall

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

hips

-0.79

sight

-0.67

manship

-0.67

 Cosponsors

-0.65

 Turing

-0.63

making

-0.63

 Progress

-0.62

makers

-0.60

lessly

-0.60

 Candy

-0.60

POSITIVE LOGITS

isine

1.49

adra

0.99

pper

0.97

pping

0.95

PLIC

0.94

arter

0.93

isin

0.92

untu

0.91

adr

0.90

illin

0.90

Activations Density 6.887%

contact information related to a product recall

No Comments

No Known Activations