INDEX

Explanations

phrases related to promotional offers and updates

oai_token-act-pair · gpt-3.5-turbo

phrases related to promotional content and marketing offers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

walk

-0.71

Registered

-0.67

ivas

-0.67

ndum

-0.65

lly

-0.65

naire

-0.63

iaries

-0.63

Ã¨re

-0.62

closed

-0.62

gged

-0.62

POSITIVE LOGITS

 occasional

0.88

 intrusive

0.69

oup

0.67

Subscribe

0.65

)=(

0.64

 perpetually

0.59

 promotions

0.59

 disclaim

0.59

 informative

0.58

 updates

0.58

Activations Density 0.048%

phrases related to promotional offers and updates

phrases related to promotional content and marketing offers

No Comments

No Known Activations