INDEX

Explanations

words related to specific locations or regions, specifically focusing on the state of New York

oai_token-act-pair · gpt-3.5-turbo

mentions of the state of New York or related entities

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

DragonMagazine

-0.77

ONSORED

-0.76

terday

-0.67

ï¸ı

-0.66

Reloaded

-0.66

pless

-0.65

icent

-0.65

 acron

-0.61

 surv

-0.61

IRD

-0.60

POSITIVE LOGITS

 York

1.62

 Hampshire

1.48

 Jersey

1.47

 Orleans

1.44

 Zealand

1.35

 Yorkers

1.33

 Brunswick

1.28

 Yorker

1.22

York

1.20

 Mexico

1.17

Activations Density 0.042%

words related to specific locations or regions, specifically focusing on the state of New York

mentions of the state of New York or related entities

No Comments

No Known Activations