INDEX

Explanations

phrases related to actions and commands

oai_token-act-pair · gpt-3.5-turbo

the end of the document or a completion indicator

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

 Niet

-0.59

 Caucas

-0.58

livious

-0.57

 tragically

-0.57

 Vaugh

-0.57

Chart

-0.57

 mirac

-0.56

 undermin

-0.56

 transpired

-0.54

 vulner

-0.54

POSITIVE LOGITS

âĦ¢:

0.66

 yourselves

0.65

 largeDownload

0.65

ye

0.64

your

0.62

0.61

 YOUR

0.61

 english

0.60

 your

0.60

DragonMagazine

0.59

Activations Density 0.291%

phrases related to actions and commands

the end of the document or a completion indicator

No Comments

No Known Activations