INDEX

Explanations

notifications or references to notifications

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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.74

nic

-0.74

urdue

-0.73

bole

-0.73

elf

-0.70

san

-0.70

 improvised

-0.69

 Falk

-0.68

ffer

-0.67

sen

-0.66

POSITIVE LOGITS

 notifications

1.24

 notification

1.13

 alerts

1.02

 notify

1.01

 Notification

0.97

 notified

0.91

 subscribers

0.87

 Subscribe

0.84

imei

0.81

 notices

0.79

Activations Density 0.012%

notifications or references to notifications

terms related to notifications

No Comments

No Known Activations