INDEX

Explanations

keywords related to notifications or alerts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "notice" and its various contexts

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

ãĥ³ãĤ¸

-0.73

iera

-0.67

ECD

-0.67

via

-0.65

ccording

-0.64

EVA

-0.63

quer

-0.63

ourke

-0.63

srf

-0.62

UES

-0.62

POSITIVE LOGITS

 notice

1.19

 Notice

1.08

 notices

1.06

notice

0.99

Notice

0.91

 NOTICE

0.87

andum

0.83

lication

0.80

ibl

0.77

ably

0.75

Activations Density 0.007%

keywords related to notifications or alerts

occurrences of the word "notice" and its various contexts

No Comments

No Known Activations