INDEX

Explanations

written words on objects or body parts

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

quickShipAvailable

-0.83

 facult

-0.74

hesda

-0.74

cong

-0.72

ugh

-0.70

brates

-0.70

emis

-0.70

leans

-0.70

forts

-0.69

hun

-0.69

POSITIVE LOGITS

 etched

1.00

 pages

0.90

 clipboard

0.87

 billboards

0.86

 jerseys

0.84

 parchment

0.83

 asphalt

0.82

 ballots

0.81

 stickers

0.80

 pavement

0.79

Activations Density 0.182%

written words on objects or body parts

No Comments

No Known Activations