INDEX

Explanations

references to governmental departments and political figures

oai_token-act-pair · gpt-3.5-turbo

components related to governmental and legal institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Indiana

-0.89

 Hawai

-0.86

Houston

-0.85

Minnesota

-0.83

Seattle

-0.83

Texas

-0.81

Favorite

-0.80

¥µ

-0.79

NBA

-0.78

Washington

-0.78

POSITIVE LOGITS

 criticised

1.35

 apologised

1.29

 Â£

1.24

 Defence

1.17

 organising

1.17

 organised

1.17

 emphas

1.16

 programmes

1.15

 scept

1.15

 programme

1.15

Activations Density 2.438%

references to governmental departments and political figures

components related to governmental and legal institutions

No Comments

No Known Activations