INDEX

Explanations

information about the legality or illegality of actions or practices in different regions

oai_token-act-pair · gpt-3.5-turbo

mentions of the concept of legality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

0000000000000000

-0.92

çĶ°

-0.79

inventoryQuantity

-0.78

FontSize

-0.75

MpServer

-0.75

DragonMagazine

-0.74

Reviewer

-0.72

oola

-0.72

rio

-0.70

 convol

-0.69

POSITIVE LOGITS

 jurisdictions

1.14

 Canada

1.09

 accordance

1.07

 Denmark

1.04

 England

1.02

 Ireland

1.01

 Switzerland

0.99

 Australia

0.97

 Bermuda

0.97

 Germany

0.96

Activations Density 0.242%

information about the legality or illegality of actions or practices in different regions

mentions of the concept of legality in various contexts

No Comments

No Known Activations