INDEX

Explanations

mentions of India or things related to India

oai_token-act-pair · gpt-3.5-turbo

references to India and its political context

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

Weiss

-0.91

Winter

-0.90

 Sounders

-0.85

lando

-0.84

UFC

-0.79

 Welch

-0.79

ĨĴ

-0.78

 cones

-0.78

paio

-0.77

 Falcon

-0.77

POSITIVE LOGITS

 India

2.28

India

2.26

 Indian

2.11

Indian

2.09

 Hindi

2.05

 Hindu

2.03

 Gujar

1.98

 Delhi

1.94

 Modi

1.93

 Mumbai

1.91

Activations Density 0.738%

mentions of India or things related to India

references to India and its political context

No Comments

No Known Activations