INDEX

Explanations

dates and time references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Apostle

-0.67

accompan

-0.67

Ops

-0.64

yrics

-0.63

bed

-0.63

resa

-0.61

 Springfield

-0.61

 Latter

-0.60

 Gospel

-0.60

 Eclipse

-0.59

POSITIVE LOGITS

DEN

0.85

 unnoticed

0.76

iatus

0.72

bery

0.70

abouts

0.69

hemy

0.68

 hitherto

0.67

uyomi

0.65

 confined

0.65

NESS

0.64

Activations Density 9.088%

dates and time references

No Comments

No Known Activations