INDEX

Explanations

mentions or instances of the word "include" followed by a number

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

Negative Logits

acia

-0.66

stem

-0.55

ongyang

-0.53

 proble

-0.51

²¾

-0.51

 athlet

-0.50

orbit

-0.50

sis

-0.49

 exting

-0.49

CLASSIFIED

-0.48

POSITIVE LOGITS

 prominently

0.63

 Include

0.63

ãĤ½

0.57

ãĤ´

0.56

rescent

0.54

ãĥ¯

0.52

ively

0.52

 annotations

0.51

clus

0.51

++++

0.50

Activations Density 17.143%

mentions or instances of the word "include" followed by a number

No Known Activations