INDEX

Explanations

technical terms and scientific topics

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

UNCH

-0.92

ELF

-0.88

XT

-0.77

astern

-0.76

ICT

-0.74

ctor

-0.73

ITH

-0.73

IRO

-0.72

ASED

-0.72

ARP

-0.70

POSITIVE LOGITS

3.30

sburg

1.88

sie

1.72

ski

1.66

sb

1.65

sburgh

1.57

sis

1.56

sf

1.54

sch

1.49

sg

1.48

Activations Density 20.032%

technical terms and scientific topics

No Comments

No Known Activations

technical terms and scientific topics

No Comments

No Known Activations