INDEX

Explanations

variations of the letter 'P' in sequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rebels

-0.86

 diplom

-0.76

 GOODMAN

-0.68

 Breaking

-0.66

adm

-0.63

ģĸ

-0.62

 EntityItem

-0.62

 Orche

-0.61

 ancest

-0.61

 juggling

-0.61

POSITIVE LOGITS

aired

1.27

ardon

1.26

ivot

1.25

ierce

1.21

erenn

1.20

ainted

1.19

ussy

1.19

oultry

1.17

airs

1.16

ushing

1.14

Activations Density 0.032%

variations of the letter 'P' in sequences

No Comments

No Known Activations