INDEX

Explanations

phrases related to various healthcare and governmental agencies or entities

oai_token-act-pair · gpt-3.5-turbo

terms related to health, government agencies, and entities involved in regulatory or oversight functions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 embodiments

-0.74

 worldwide

-0.70

mic

-0.68

 redund

-0.68

 cavity

-0.67

 profiling

-0.66

 globally

-0.66

 gigs

-0.66

 chemotherapy

-0.66

 notch

-0.65

POSITIVE LOGITS

 Authority

1.30

 Association

1.29

 Consortium

1.20

 Commission

1.18

 Agency

1.16

 Patrol

1.14

 Cooperative

1.08

 Exchange

1.05

 Railway

1.03

 Board

1.03

Activations Density 0.205%

phrases related to various healthcare and governmental agencies or entities

terms related to health, government agencies, and entities involved in regulatory or oversight functions

No Comments

No Known Activations