INDEX

Explanations

phrases related to outcomes or results, particularly at the end of a process or action

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

she

-0.60

Bay

-0.53

NESS

-0.52

caster

-0.50

ocular

-0.49

CW

-0.49

oqu

-0.49

agall

-0.49

stead

-0.49

asking

-0.48

POSITIVE LOGITS

dos

0.55

otom

0.54

 ..........

0.53

 eaten

0.53

obal

0.53

glomer

0.53

 Schwar

0.52

 unus

0.52

ORED

0.52

OGR

0.52

Activations Density 12.959%

phrases related to outcomes or results, particularly at the end of a process or action

No Comments

No Known Activations