INDEX

Explanations

words related to past events or histories

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

UTF

-0.62

SourceFile

-0.56

suggest

-0.55

DOS

-0.55

utf

-0.55

Mach

-0.54

Cas

-0.51

Cho

-0.51

DERR

-0.51

soDeliveryDate

-0.51

POSITIVE LOGITS

erous

0.69

etime

0.64

bidden

0.62

ideshow

0.62

pired

0.59

adies

0.58

idth

0.57

ivable

0.57

astered

0.54

eatures

0.53

Activations Density 5.379%

words related to past events or histories

No Comments

No Known Activations