INDEX

Explanations

phrases containing locations or places

oai_token-act-pair · gpt-3.5-turbo

geographic references related to cities or regions

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

ITION

-0.72

 pend

-0.67

xual

-0.67

 inhibitors

-0.65

hemy

-0.64

 spores

-0.63

emort

-0.63

 parasites

-0.63

 implants

-0.63

 pedals

-0.62

POSITIVE LOGITS

 suburbs

1.17

 metropolitan

1.11

 metro

1.10

 suburb

1.03

 Chinatown

1.00

 Downtown

0.99

 borough

0.95

quartered

0.93

area

0.88

 suburban

0.88

Activations Density 0.267%

phrases containing locations or places

geographic references related to cities or regions

No Comments

No Known Activations