INDEX

Explanations

references and citations in scientific publications

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

 furn

-0.61

asionally

-0.61

ndra

-0.60

urally

-0.59

ween

-0.59

 taxp

-0.58

reon

-0.58

orate

-0.56

 Shay

-0.56

ez

-0.55

POSITIVE LOGITS

0.96

0.83

0.78

0.73

0.71

ãĥł

0.69

0.66

 Journals

0.65

Activations Density 5.343%

references and citations in scientific publications

No Comments

No Known Activations