INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

soDeliveryDate

-0.87

 ILCS

-0.84

 Flavoring

-0.78

prus

-0.76

omever

-0.74

orthy

-0.73

wives

-0.70

vard

-0.70

ocene

-0.67

icum

-0.67

POSITIVE LOGITS

 ours

1.42

 yours

1.29

 hers

1.27

 theirs

1.19

 mine

0.88

 madness

0.72

 carnage

0.72

 fate

0.71

 behavior

0.67

 behalf

0.65

Activations Density 0.150%

locations or places

phrases that indicate possession or ownership

No Comments

No Known Activations