INDEX

Explanations

notifications or alerts in a text

oai_token-act-pair · gpt-3.5-turbo

terms related to notifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

tern

-0.69

private

-0.65

creat

-0.63

-0.62

sen

-0.62

à¸

-0.62

ny

-0.62

 Falk

-0.62

aughs

-0.62

exec

-0.61

POSITIVE LOGITS

 notifications

1.33

 notification

1.23

 Notification

1.03

 alerts

0.91

imei

0.88

 notify

0.87

 notified

0.84

ariat

0.77

 notices

0.76

ategory

0.76

Activations Density 0.007%

notifications or alerts in a text

terms related to notifications

No Comments

No Known Activations