INDEX

Explanations

computer programming-related terms and code snippets within text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

0000000000000000

-0.74

owship

-0.74

 Canaveral

-0.71

iasis

-0.70

toc

-0.67

according

-0.67

alle

-0.66

cise

-0.66

appiness

-0.66

cession

-0.65

POSITIVE LOGITS

ĨĴ

0.80

 conventions

0.75

 convention

0.73

£ı

0.73

 "$:/

0.70

uay

0.65

 terminology

0.64

ĻĤ

0.64

 Experiment

0.63

 experimenting

0.63

Activations Density 8.750%

computer programming-related terms and code snippets within text

No Comments

No Known Activations