INDEX

Explanations

references to North Korea and related topics, specifically in the context of political, military, and nuclear discussions

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

igue

-0.95

MENTS

-0.93

++++++++++++++++

-0.91

hent

-0.83

llo

-0.80

Baltimore

-0.79

ments

-0.79

MENT

-0.79

Tags

-0.78

gerald

-0.77

POSITIVE LOGITS

orea

1.10

 blackmail

0.98

 defect

0.96

 detonated

0.90

 meltdown

0.88

 Pyongyang

0.87

 missile

0.85

ì

0.84

 desp

0.83

ongyang

0.82

Activations Density 5.474%

references to North Korea and related topics, specifically in the context of political, military, and nuclear discussions

No Comments

No Known Activations