INDEX

Explanations

phrases related to rules, regulations, and guidelines

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

HCR

-0.72

åī

-0.69

terness

-0.68

İĭ

-0.68

 à¨

-0.63

olor

-0.63

ãĤ´ãĥ³

-0.60

£ı

-0.57

elsen

-0.57

 Noon

-0.56

POSITIVE LOGITS

 reasonably

0.65

 profitable

0.58

 comprehend

0.58

aeus

0.55

 practicable

0.54

 progressed

0.53

appropriate

0.52

areth

0.52

 feasible

0.51

 uninterrupted

0.51

Activations Density 14.259%

phrases related to rules, regulations, and guidelines

No Comments

No Known Activations