INDEX

Explanations

texts related to malicious activities or intentions

oai_token-act-pair · gpt-3.5-turbo

examples of malicious behavior or intent

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-1.40

akeru

-0.84

arist

-0.84

orus

-0.82

marks

-0.80

uesday

-0.79

gdala

-0.78

ills

-0.76

Vert

-0.76

ļéĨĴ

-0.76

POSITIVE LOGITS

ly

1.16

 intent

0.98

 implant

0.83

 payload

0.83

 mischief

0.79

 behaviour

0.79

vertising

0.76

 actors

0.75

 behavior

0.74

 malicious

0.73

Activations Density 0.017%

texts related to malicious activities or intentions

examples of malicious behavior or intent

No Comments

No Known Activations