INDEX

Explanations

tech-related terms and programming discussion

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

SourceFile

-0.80

è¦ļéĨĴ

-0.72

 portfolios

-0.70

 portfolio

-0.64

 ecosystem

-0.62

 orche

-0.57

 flora

-0.56

ahan

-0.55

 capsule

-0.55

 cart

-0.55

POSITIVE LOGITS

adays

0.94

 THERE

0.85

here

0.82

asus

0.77

 thankfully

0.70

ciating

0.67

 begs

0.67

herer

0.66

 lets

0.65

thodox

0.63

Activations Density 13.278%

tech-related terms and programming discussion

No Comments

No Known Activations

tech-related terms and programming discussion

No Comments

No Known Activations