INDEX

Explanations

phrases related to locations or addresses

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

 reproduce

-0.69

 litres

-0.67

 squads

-0.66

onom

-0.66

berman

-0.65

 suits

-0.64

rogram

-0.63

orians

-0.62

 adaptations

-0.62

arian

-0.62

POSITIVE LOGITS

Rd

1.04

NW

0.99

 Junction

0.92

 intersection

0.91

 Blvd

0.87

 Northeast

0.86

 Cemetery

0.86

 Parkway

0.86

 Boulevard

0.86

wy

0.85

Activations Density 0.045%

phrases related to locations or addresses

No Comments

No Known Activations