INDEX

Explanations

references to the name "Justin" or "Bieber."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ktop

-0.76

wark

-0.74

 extremes

-0.70

 mileage

-0.69

rums

-0.66

exempt

-0.66

 confinement

-0.66

ansas

-0.64

 womb

-0.63

unda

-0.63

POSITIVE LOGITS

 Bieber

1.38

 Timber

1.18

 Trudeau

1.02

 Vernon

0.91

 Upton

0.90

 Wong

0.85

 Hayward

0.84

 Bour

0.84

Justin

0.83

onymous

0.82

Activations Density 0.006%

references to the name "Justin" or "Bieber."

No Comments

No Known Activations