INDEX

Explanations

descriptions of potential obstacles and challenges

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

 hemor

-0.76

 majority

-0.74

blind

-0.73

heter

-0.72

majority

-0.72

 Bates

-0.72

opath

-0.72

parents

-0.71

 abuser

-0.70

 Submission

-0.69

POSITIVE LOGITS

 glean

0.91

uable

0.88

 Done

0.87

 Learned

0.86

arios

0.85

itas

0.80

 worth

0.79

 Squadron

0.79

 takeaway

0.77

ario

0.76

Activations Density 19.166%

descriptions of potential obstacles and challenges

No Comments

No Known Activations