INDEX

Explanations

words related to fraudulent activities or schemes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "scam" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

FK

-0.68

 Atom

-0.68

IFE

-0.67

 Borders

-0.63

itarian

-0.62

hani

-0.61

 Olive

-0.61

 Differences

-0.60

 temperature

-0.57

éĹĺ

-0.57

POSITIVE LOGITS

ulent

1.31

ulence

1.11

pering

1.07

sters

1.05

crow

0.92

ulously

0.90

 perpetrated

0.89

atown

0.89

 scam

0.87

ster

0.87

Activations Density 0.049%

words related to fraudulent activities or schemes

occurrences of the word "scam" and related terms

No Comments

No Known Activations