INDEX

Explanations

mentions of technical terms and programming code

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

Wan

-0.65

Result

-0.58

olicited

-0.58

STR

-0.58

ail

-0.58

empty

-0.57

enda

-0.57

ravis

-0.57

igh

-0.57

POSITIVE LOGITS

ĨĴ

0.73

 loopholes

0.71

 compens

0.70

 quirks

0.70

 permitting

0.70

 shielding

0.69

 protections

0.68

 allowing

0.68

 patented

0.67

 legalized

0.67

Activations Density 19.021%

mentions of technical terms and programming code

No Comments

No Known Activations