INDEX

Explanations

references to or related to the country "Malaysia"

oai_token-act-pair · gpt-3.5-turbo

mentions and references to Malaysia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptions

-0.79

á½

-0.76

ebook

-0.74

ãĤ½

-0.70

å§

-0.70

ä

-0.69

BOOK

-0.69

bern

-0.68

enegger

-0.67

-0.66

POSITIVE LOGITS

 Lumpur

1.64

 Airlines

1.41

 Abdul

0.83

 airliner

0.83

colm

0.83

awi

0.82

daq

0.82

sey

0.80

 airlines

0.80

ovic

0.79

Activations Density 0.015%

references to or related to the country "Malaysia"

mentions and references to Malaysia

No Comments

No Known Activations