INDEX

Explanations

mentions of legal actions involving specific numbers and people or organizations

oai_token-act-pair · gpt-3.5-turbo

instances of legal punishment or sentencing

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Chuck

-0.80

adelphia

-0.77

 Fallon

-0.76

Utah

-0.74

 Whitman

-0.73

Jeff

-0.72

 Jefferson

-0.71

Kyle

-0.70

Madison

-0.69

Ted

-0.69

POSITIVE LOGITS

 Azerbai

1.16

ÄŁ

1.15

NGO

1.04

ÅŁ

1.02

 Azerbaijan

1.01

 Bulgarian

1.01

 Rohingya

1.00

 Armenian

1.00

Ä

0.98

 Armenia

0.98

Activations Density 2.029%

mentions of legal actions involving specific numbers and people or organizations

instances of legal punishment or sentencing

No Comments

No Known Activations