INDEX

Explanations

locations or settings in news articles

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" and phrases related to locations or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

DragonMagazine

-0.85

 accordingly

-0.79

MpServer

-0.79

phabet

-0.75

OTUS

-0.74

niper

-0.72

abis

-0.72

adder

-0.71

wx

-0.71

ANS

-0.70

POSITIVE LOGITS

 Peru

1.03

 Thailand

1.02

 Seoul

1.00

 Pennsylvania

0.99

 California

0.98

 Guatemala

0.97

 rural

0.96

 Japan

0.96

 Florida

0.95

 southwestern

0.95

Activations Density 0.246%

locations or settings in news articles

instances of the word "in" and phrases related to locations or contexts

No Comments

No Known Activations