INDEX

Explanations

mentions of the malware "Cerber"

oai_token-act-pair · gpt-3.5-turbo

specific references to the word "Cer" and its variations in different contexts

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

ski

-0.98

ers

-0.90

erness

-0.80

wich

-0.78

 Barkley

-0.78

sburg

-0.78

-0.77

urst

-0.76

ingly

-0.75

ership

-0.75

POSITIVE LOGITS

 millenn

0.95

berus

0.86

emetery

0.81

elsius

0.78

ablish

0.77

aleigh

0.73

ablishment

0.71

 corrid

0.70

 Dame

0.69

zza

0.69

Activations Density 0.041%

mentions of the malware "Cerber"

specific references to the word "Cer" and its variations in different contexts

No Comments

No Known Activations