INDEX

Explanations

specific details or elements mentioned in a document, such as provisions, requirements, and components

oai_token-act-pair · gpt-3.5-turbo

items or provisions listed in a document

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

 Thornton

-0.71

enium

-0.68

imaru

-0.67

cules

-0.67

yan

-0.66

ades

-0.65

 nowhere

-0.63

anes

-0.63

 Wander

-0.62

atis

-0.62

POSITIVE LOGITS

âĹı

0.94

âĸł

0.94

âľ

0.89

âĢ¢

0.84

âĺħ

0.78

Â·

0.73

BuyableInstoreAndOnline

0.71

ðĿ

0.67

AUT

0.67

 âĹı

0.66

Activations Density 0.127%

specific details or elements mentioned in a document, such as provisions, requirements, and components

items or provisions listed in a document

No Comments

No Known Activations