INDEX

Explanations

questions or statements inquiring about the origin of something

oai_token-act-pair · gpt-3.5-turbo

phrases that inquire about origins or sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aples

-0.66

enture

-0.61

©¶æ

-0.61

hemy

-0.60

gone

-0.59

asio

-0.58

bably

-0.57

visors

-0.56

eatures

-0.56

cape

-0.56

POSITIVE LOGITS

Ø§

0.62

ument

0.62

Sense

0.57

Border

0.55

Ã£

0.54

 sting

0.53

ood

0.53

oct

0.53

 unst

0.52

owship

0.52

Activations Density 0.021%

questions or statements inquiring about the origin of something

phrases that inquire about origins or sources

No Comments

No Known Activations