INDEX

Explanations

references to quantities or measurements

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.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

 plagiar

-0.83

 treason

-0.80

 traitor

-0.75

 congrat

-0.75

 adultery

-0.73

 deceit

-0.73

 Libertarian

-0.73

 scorn

-0.72

 Attribution

-0.70

 epigen

-0.70

POSITIVE LOGITS

 capacity

1.38

 throughput

1.21

capacity

1.19

 Capacity

1.14

 accommodate

1.14

 quota

1.12

 manpower

1.12

 occupancy

1.11

 overcrowd

1.07

 accommod

1.07

Activations Density 0.832%

references to quantities or measurements

No Comments

No Known Activations