INDEX

Explanations

information related to legal terms, author declarations, and copyright statements in scientific publications

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

illon

-0.43

Insp

-0.41

course

-0.41

 Mississ

-0.40

 Jenner

-0.40

ghazi

-0.39

 coli

-0.39

 Khal

-0.39

Ivy

-0.39

Wr

-0.39

POSITIVE LOGITS

earchers

0.57

Ô

0.47

licts

0.46

urances

0.45

mble

0.44

nants

0.44

ernels

0.43

 Minority

0.43

addin

0.43

 neutrality

0.41

Activations Density 0.264%

information related to legal terms, author declarations, and copyright statements in scientific publications

No Comments

No Known Activations