INDEX

Explanations

phrases related to agreeing to receive special offers from a specific source

oai_token-act-pair · gpt-3.5-turbo

phrases related to promotional offers and subscriptions

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

aukee

-0.65

neapolis

-0.61

////////////////////////////////

-0.59

forth

-0.58

staff

-0.58

 Leilan

-0.57

ahu

-0.57

llan

-0.56

Û

-0.56

 Logged

-0.55

POSITIVE LOGITS

 subscribing

0.85

 giveaways

0.85

obe

0.70

ifestyle

0.63

 sale

0.61

 goodies

0.60

interstitial

0.60

 promotions

0.59

gotten

0.58

 subscriptions

0.58

Activations Density 0.031%

phrases related to agreeing to receive special offers from a specific source

phrases related to promotional offers and subscriptions

No Comments

No Known Activations