INDEX

Explanations

mathematical terms related to squares

oai_token-act-pair · gpt-3.5-turbo

references to geometric shapes, specifically squares

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

 Seller

-0.66

 Donation

-0.66

ARP

-0.65

ortium

-0.65

 confidentiality

-0.64

bach

-0.62

 appropri

-0.62

essee

-0.61

 Appropriations

-0.60

 Gloss

-0.60

POSITIVE LOGITS

 Enix

1.12

µ

0.88

©¶æ

0.80

³

0.78

pants

0.78

 metre

0.77

bors

0.76

cus

0.76

 scrimmage

0.76

 kilomet

0.76

Activations Density 0.012%

mathematical terms related to squares

references to geometric shapes, specifically squares

No Comments

No Known Activations