INDEX

Explanations

mentions of political figures, particularly President Donald Trump

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nexus

-1.09

 arteries

-0.94

ocr

-0.93

oned

-0.92

-0.89

fman

-0.86

onal

-0.85

Reviewed

-0.84

bred

-0.83

 applic

-0.82

POSITIVE LOGITS

swer

1.21

 Trump

1.06

Taj

1.04

 Donald

1.02

 Fallon

0.99

ª

0.99

\\\\\\\\

0.99

¼

0.95

 Enrique

0.94

mares

0.94

Activations Density 0.465%

mentions of political figures, particularly President Donald Trump

No Comments

No Known Activations