INDEX

Explanations

references to hacking activities or hackers

oai_token-act-pair · gpt-3.5-turbo

references to hacking and hacker groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Towns

-0.80

eele

-0.79

urn

-0.72

illard

-0.69

 Leban

-0.67

IX

-0.67

BuyableInstoreAndOnline

-0.67

Buyable

-0.67

âĶĢâĶĢâĶĢâĶĢ

-0.65

ruciating

-0.65

POSITIVE LOGITS

 hackers

0.99

intosh

0.94

paces

0.94

 hacker

0.92

 extraord

0.86

 hacking

0.78

RF

0.78

aday

0.75

haw

0.73

netic

0.73

Activations Density 0.018%

references to hacking activities or hackers

references to hacking and hacker groups

No Comments

No Known Activations