INDEX

Explanations

proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific entities

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

 Kraken

-0.70

 Boone

-0.70

ilings

-0.68

iator

-0.67

assetsadobe

-0.67

ishable

-0.65

 paperback

-0.63

 speedy

-0.63

iles

-0.63

 Airbnb

-0.62

POSITIVE LOGITS

âĢ

1.23

Â

1.00

0.99

Â¢

0.98

Â´

0.97

âĪ

0.96

âĢ²

0.96

0.94

'/

0.93

0.92

Activations Density 0.215%

proper nouns or specific names

proper nouns and specific entities

No Comments

No Known Activations