INDEX

Explanations

ecommerce-related terms or company names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of companies, characters, and significant entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

¶ħ

-0.54

lihood

-0.48

 Katy

-0.48

ãĥĩãĤ£

-0.47

ãĥ©ãĥ³

-0.47

Ire

-0.47

 ..."

-0.47

é¾įå¥ĳå£«

-0.46

Redd

-0.46

ãĥ¼ãĥĨãĤ£

-0.45

POSITIVE LOGITS

 behaves

0.66

 possesses

0.60

 enjoys

0.59

's

0.58

 underwent

0.57

 suffers

0.57

 excel

0.55

 consists

0.55

 behaved

0.55

 spends

0.54

Activations Density 0.622%

ecommerce-related terms or company names

proper nouns, particularly names of companies, characters, and significant entities

No Comments

No Known Activations