INDEX

Explanations

dates, including years

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

acci

-0.74

vertisement

-0.62

 Skinner

-0.62

 proport

-0.61

illet

-0.60

icone

-0.57

abilia

-0.57

rouse

-0.57

plain

-0.56

andise

-0.55

POSITIVE LOGITS

GV

0.81

TED

0.68

âĢ¢âĢ¢

0.67

 Nicol

0.65

 Tosh

0.64

Guard

0.63

gur

0.62

BILL

0.62

AMY

0.61

å¹

0.61

Activations Density 11.524%

dates, including years

No Comments

No Known Activations