INDEX

Explanations

locations or venues, particularly with the word "Plaza" in them

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or plazas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

went

-0.77

ebook

-0.75

gets

-0.75

wcsstore

-0.71

ERAL

-0.69

nesses

-0.69

liest

-0.68

loss

-0.67

young

-0.65

dit

-0.64

POSITIVE LOGITS

 Plaza

1.45

 plaza

1.15

 Hotel

0.93

 Square

0.84

 Coliseum

0.82

emonium

0.82

 Blvd

0.81

itect

0.81

 Corridor

0.79

 kios

0.78

Activations Density 0.008%

locations or venues, particularly with the word "Plaza" in them

references to specific locations or plazas

No Comments

No Known Activations