INDEX

Explanations

places of origin

oai_token-act-pair · gpt-3.5-turbo

phrases indicating origin or hometown

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

airs

-0.79

aminer

-0.79

 challeng

-0.78

TPPStreamerBot

-0.76

seek

-0.71

uden

-0.69

perty

-0.68

phabet

-0.68

aed

-0.67

hooting

-0.67

POSITIVE LOGITS

 afar

1.08

 abroad

0.95

 whence

0.81

 overseas

0.80

 nowhere

0.79

 rural

0.79

 scratch

0.77

 Poland

0.77

 Czech

0.75

 Generation

0.74

Activations Density 0.076%

places of origin

phrases indicating origin or hometown

No Comments

No Known Activations