INDEX

Explanations

questions ending with a question mark

oai_token-act-pair · gpt-3.5-turbo

questions that prompt inquiry or exploration

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

belt

-0.75

ishable

-0.68

mia

-0.68

lam

-0.67

 haul

-0.67

mot

-0.65

 booked

-0.65

nar

-0.64

bole

-0.64

lining

-0.63

POSITIVE LOGITS

 Nope

1.08

 Lastly

1.04

 Answer

0.99

 Flavoring

0.99

Et

0.97

 Finally

0.96

 Whatever

0.95

 Inqu

0.95

 Conversely

0.94

 Perhaps

0.93

Activations Density 0.054%

questions ending with a question mark

questions that prompt inquiry or exploration

No Comments

No Known Activations