INDEX

Explanations

references to large quantities of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating large quantities, particularly those referring to "tens of thousands" or "tens of millions."

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

 holder

-0.66

mint

-0.64

 Slayer

-0.63

 Colony

-0.62

 Boards

-0.62

 Shrine

-0.62

 Providence

-0.62

arette

-0.61

 Bomber

-0.61

igion

-0.60

POSITIVE LOGITS

omet

0.99

ourcing

0.95

atile

0.94

atility

0.92

eteen

0.89

elfth

0.88

earchers

0.87

imet

0.86

uador

0.85

rolet

0.85

Activations Density 0.010%

references to large quantities of something

phrases indicating large quantities, particularly those referring to "tens of thousands" or "tens of millions."

No Comments

No Known Activations