INDEX

Explanations

references to specific human body organs, especially the liver

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tolerance

-0.84

FACE

-0.76

ï¸ı

-0.73

teen

-0.72

 Penet

-0.71

IGH

-0.70

Eag

-0.69

 Goose

-0.68

NESS

-0.68

Gaw

-0.68

POSITIVE LOGITS

izational

1.27

ically

1.13

izes

1.11

iser

1.09

isations

1.08

 organ

1.05

iop

1.02

 transplant

1.01

iza

0.98

izations

0.97

Activations Density 3.362%

references to specific human body organs, especially the liver

No Comments

No Known Activations