INDEX

Explanations

programming-related keywords and phrases related to software development

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mat

-0.35

 goodness

-0.34

Prem

-0.32

Uk

-0.30

nesses

-0.29

Pak

-0.29

 Earthqu

-0.29

Bey

-0.28

 looming

-0.28

 qualify

-0.28

POSITIVE LOGITS

users

0.41

ESSION

0.36

quit

0.35

sylv

0.34

anwhile

0.33

opausal

0.33

 desk

0.33

desktop

0.32

livion

0.32

vertis

0.32

Activations Density 0.036%

programming-related keywords and phrases related to software development

No Comments

No Known Activations