INDEX

Explanations

descriptions of sharpness or keenness, often relating to attributes or characteristics

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

inventoryQuantity

-0.46

isSpecialOrderable

-0.45

channelAvailability

-0.44

 Corinthians

-0.44

ICAN

-0.44

iland

-0.43

asions

-0.42

 Leia

-0.42

aceae

-0.42

 Incarn

-0.41

POSITIVE LOGITS

ened

0.61

ening

0.60

ness

0.59

 eyed

0.56

edo

0.53

ener

0.51

est

0.50

sonian

0.48

erning

0.47

bol

0.46

Activations Density 0.930%

descriptions of sharpness or keenness, often relating to attributes or characteristics

No Comments

No Known Activations