INDEX

Explanations

phrases related to legal text or documents

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

å°Ĩ

-0.37

ãĥ¼ãĥĨãĤ£

-0.35

é¾įå¥ĳå£«

-0.35

ãĤ¢ãĥ«

-0.34

terday

-0.32

USER

-0.31

cdn

-0.31

iannopoulos

-0.30

è£ħ

-0.30

lehem

-0.30

POSITIVE LOGITS

endar

0.32

 Finder

0.31

occ

0.29

abus

0.29

 affidav

0.27

 Sahara

0.27

cro

0.27

stal

0.27

ifter

0.27

 affidavit

0.26

Activations Density 0.017%

phrases related to legal text or documents

No Comments

No Known Activations