INDEX

Explanations

variations of the word "risk" often accompanied by specific keywords or phrases

oai_token-act-pair · gpt-3.5-turbo

specific special characters or symbols within the text

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

 Pony

-0.73

ukong

-0.65

 unborn

-0.64

 Samar

-0.62

 fodder

-0.61

 Seah

-0.61

 bystand

-0.60

aimon

-0.60

 Vaugh

-0.60

osaurus

-0.60

POSITIVE LOGITS

ï¸ı

1.37

ï¸

1.03

ÃĽ

0.93

catentry

0.89

taboola

0.88

Â¢

0.86

uthor

0.84

ternity

0.81

Â½

0.81

Â²

0.81

Activations Density 0.038%

variations of the word "risk" often accompanied by specific keywords or phrases

specific special characters or symbols within the text

No Comments

No Known Activations