INDEX

Explanations

mentions of controversy, political figures, and historical events related to social or political issues

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

YA

-0.78

istries

-0.72

 Starr

-0.71

hetti

-0.68

xit

-0.68

ELS

-0.67

auga

-0.67

enthal

-0.65

 Dragonbound

-0.65

Phill

-0.65

POSITIVE LOGITS

isively

1.12

iving

1.05

ider

0.92

mal

0.90

isive

0.89

anged

0.88

bies

0.84

ively

0.77

iding

0.76

ping

0.76

Activations Density 6.932%

mentions of controversy, political figures, and historical events related to social or political issues

No Comments

No Known Activations