INDEX

Explanations

references to the country Saudi Arabia

oai_token-act-pair · gpt-3.5-turbo

mentions of Saudi Arabia and its associations

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

mble

-0.90

schild

-0.88

eon

-0.78

lest

-0.76

 Myster

-0.71

 Puzz

-0.71

estern

-0.70

matter

-0.69

 Matter

-0.68

 Repair

-0.67

POSITIVE LOGITS

 Arabia

1.89

 Arabian

1.49

 Aram

1.12

istani

0.89

 princes

0.86

 nationals

0.82

 Abdullah

0.79

 Arab

0.79

istan

0.77

 prince

0.74

Activations Density 0.010%

references to the country Saudi Arabia

mentions of Saudi Arabia and its associations

No Comments

No Known Activations