INDEX

Explanations

organizations and associations, specifically focusing on their affiliations or origins

oai_token-act-pair · gpt-3.5-turbo

references to organizations and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

?]

-0.72

...]

-0.72

 arsen

-0.70

 spoil

-0.70

 heap

-0.69

ItemTracker

-0.69

inventoryQuantity

-0.68

âĢ¦]

-0.66

 summ

-0.66

few

-0.65

POSITIVE LOGITS

 America

1.29

 Greater

1.27

 Canada

1.12

 Americas

1.11

 Pennsylvania

1.08

 Excellence

1.04

 Australia

1.04

 Ireland

1.04

 California

1.03

 Philadelphia

1.00

Activations Density 0.073%

organizations and associations, specifically focusing on their affiliations or origins

references to organizations and associations

No Comments

No Known Activations