INDEX

Explanations

statistics, numbers, and names related to geographical and political events

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

£ı

-0.74

 Heller

-0.73

 vanity

-0.73

 swearing

-0.72

Reviewer

-0.71

 alienation

-0.70

 descending

-0.70

assetsadobe

-0.68

Tob

-0.68

 Militia

-0.67

POSITIVE LOGITS

Â½

1.41

 Â½

1.08

PO

1.07

nd

1.05

1.02

0.99

0.98

DP

0.98

PDF

0.96

0.95

Activations Density 6.612%

statistics, numbers, and names related to geographical and political events

No Comments

No Known Activations