INDEX

Explanations

words related to products and accessories

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

luck

-0.61

rolled

-0.60

zee

-0.56

bow

-0.56

keye

-0.55

ukemia

-0.55

 Archdemon

-0.54

awar

-0.54

\\\\\\\\

-0.54

apers

-0.54

POSITIVE LOGITS

 accessory

0.74

 accessories

0.65

 peripher

0.64

MpServer

0.60

 Accessories

0.56

Accessory

0.54

 thereto

0.54

 retailer

0.52

 Vend

0.51

 cables

0.50

Activations Density 8.511%

words related to products and accessories

No Comments

No Known Activations