INDEX

Explanations

terms related to religious figures and beliefs, focusing on saints, mystics, and philosophers in various cultures and historical contexts

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

 increments

-0.53

ãĤ¯

-0.52

Owner

-0.48

 srfAttach

-0.48

stre

-0.47

inventoryQuantity

-0.46

Delivery

-0.45

 è£ıè

-0.44

 inspections

-0.44

Fly

-0.44

POSITIVE LOGITS

aurus

0.91

paces

0.89

ervatives

0.86

ervative

0.84

hip

0.77

ktop

0.75

hips

0.74

alam

0.72

pace

0.70

ophical

0.68

Activations Density 13.167%

terms related to religious figures and beliefs, focusing on saints, mystics, and philosophers in various cultures and historical contexts

No Comments

No Known Activations