INDEX

Explanations

technical terms related to computer systems and infrastructure

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

iage

-0.75

ersive

-0.74

llor

-0.67

 conclud

-0.65

=-=-=-=-=-=-=-=-

-0.65

utical

-0.64

iard

-0.64

ãĤ¼ãĤ¦ãĤ¹

-0.63

uate

-0.59

 artific

-0.58

POSITIVE LOGITS

SSL

0.84

Street

0.83

BSD

0.73

Indiana

0.69

office

0.67

Aren

0.67

street

0.64

liness

0.63

 Container

0.62

eport

0.61

Activations Density 7.708%

technical terms related to computer systems and infrastructure

No Comments

No Known Activations