INDEX

Explanations

conspiratorial and politically charged language

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

 Reincarn

-0.74

 Seym

-0.74

 limb

-0.73

 Stras

-0.73

 condem

-0.72

 tabloid

-0.72

 Tanz

-0.70

 Vaugh

-0.69

 Citiz

-0.68

 landmarks

-0.68

POSITIVE LOGITS

ï¸ı

1.25

lean

1.01

company

0.97

vernment

0.95

Balt

0.93

lime

0.93

ever

0.93

wow

0.92

agree

0.91

pol

0.90

Activations Density 6.015%

conspiratorial and politically charged language

No Comments

No Known Activations