INDEX

Explanations

words related to a mathematical concept involving the square root

oai_token-act-pair · gpt-3.5-turbo

references to the geometric concept of "square."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ARP

-0.79

 Referred

-0.69

 Seller

-0.66

esta

-0.63

iesel

-0.62

oan

-0.62

 Helpful

-0.62

 Gloss

-0.61

INA

-0.60

 Claus

-0.59

POSITIVE LOGITS

 Enix

1.09

 square

0.96

 squares

0.94

Square

0.87

square

0.86

 squared

0.79

©¶æ

0.77

 spacing

0.75

 grids

0.73

 Square

0.73

Activations Density 0.012%

words related to a mathematical concept involving the square root

references to the geometric concept of "square."

No Comments

No Known Activations