INDEX

Explanations

symbols or punctuation used as emphasis or separation within text

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and special characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

bledon

-0.58

estones

-0.53

elfth

-0.52

abee

-0.50

avia

-0.50

elve

-0.49

 Exploration

-0.49

 fields

-0.48

 Aware

-0.47

entials

-0.47

POSITIVE LOGITS

ãħĭãħĭ

0.61

ASHINGTON

0.60

 partName

0.59

please

0.59

 ..........

0.59

âĹ¼

0.58

):

0.58

)?

0.57

————

0.57

DragonMagazine

0.55

Activations Density 0.384%

symbols or punctuation used as emphasis or separation within text

punctuation marks and special characters in the text

No Comments

No Known Activations