INDEX

Explanations

references to future events or entities, specifically in the context of financial markets and technology

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

apy

-0.63

artney

-0.60

ysis

-0.60

 waters

-0.57

 sclerosis

-0.57

 slopes

-0.54

realDonaldTrump

-0.54

river

-0.53

 disinfect

-0.51

 Piercing

-0.49

POSITIVE LOGITS

ility

0.90

urity

0.72

ures

0.71

uristic

0.70

bol

0.67

ulence

0.65

ilitarian

0.63

uro

0.61

alist

0.60

zing

0.60

Activations Density 7.241%

references to future events or entities, specifically in the context of financial markets and technology

No Comments

No Known Activations