INDEX

Explanations

phrases related to checking out publications or subscribing for more content

oai_token-act-pair · gpt-3.5-turbo

calls to action related to subscriptions or following content

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

course

-0.59

 Puzzles

-0.59

 embr

-0.58

eers

-0.58

Nib

-0.57

soever

-0.55

cknowled

-0.55

 acknowled

-0.54

 assumes

-0.54

 scram

-0.53

POSITIVE LOGITS

çīĪ

0.69

bleacher

0.66

utenberg

0.63

BBC

0.62

Subscribe

0.61

aic

0.59

çİĭ

0.57

inventoryQuantity

0.57

sports

0.57

amacare

0.56

Activations Density 0.078%

phrases related to checking out publications or subscribing for more content

calls to action related to subscriptions or following content

No Comments

No Known Activations