INDEX

Explanations

details of recipes, ingredients, and cooking instructions

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

dfx

-0.62

CRIP

-0.60

è»

-0.59

psey

-0.57

ovych

-0.55

achev

-0.55

ricular

-0.55

éĹĺ

-0.55

atron

-0.54

milo

-0.53

POSITIVE LOGITS

 Traditional

0.51

 Basic

0.49

 Gina

0.47

 CNBC

0.46

reads

0.46

 Legs

0.44

DIY

0.44

 Notting

0.44

 Chop

0.43

 Patty

0.43

Activations Density 8.870%

details of recipes, ingredients, and cooking instructions

No Comments

No Known Activations