INDEX

Explanations

words related to notifications

oai_token-act-pair · gpt-3.5-turbo

terms related to notifications and alerts in applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tern

-0.89

enes

-0.79

rina

-0.76

san

-0.75

tto

-0.74

enic

-0.74

tre

-0.73

bole

-0.70

CTV

-0.70

elf

-0.69

POSITIVE LOGITS

 notifications

1.16

 notification

1.00

 alerts

0.96

 Notification

0.88

 notify

0.86

 notices

0.78

 prompts

0.77

 inbox

0.76

 subscribers

0.76

 Subscribe

0.74

Activations Density 0.020%

words related to notifications

terms related to notifications and alerts in applications

No Comments

No Known Activations