INDEX

Explanations

words related to malicious software or computer infections

oai_token-act-pair · gpt-3.5-turbo

references to malware and ransomware

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

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.84

UTC

-0.78

arist

-0.75

ffen

-0.74

 Yards

-0.74

ilts

-0.73

obar

-0.71

abouts

-0.71

alist

-0.70

rite

-0.69

POSITIVE LOGITS

bytes

0.96

 malware

0.95

 Mehran

0.84

 infection

0.83

 infections

0.82

 infect

0.81

eware

0.80

 outbreak

0.76

 payload

0.75

WARE

0.75

Activations Density 0.036%

words related to malicious software or computer infections

references to malware and ransomware

No Comments

No Known Activations