INDEX

Explanations

words related to criminal activities, particularly first-degree murder

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "first-person" in relation to crimes and legal matters

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

 Canaver

-0.80

 Blanc

-0.66

 Richards

-0.64

Downloadha

-0.64

 Sawyer

-0.63

 lubric

-0.63

âĸĵ

-0.63

 Rath

-0.62

ulkan

-0.60

âĸĴ

-0.59

POSITIVE LOGITS

degree

1.10

generation

1.09

class

0.98

contact

0.97

ever

0.94

level

0.92

chance

0.92

party

0.90

century

0.90

eyed

0.88

Activations Density 0.022%

words related to criminal activities, particularly first-degree murder

instances of the phrase "first-person" in relation to crimes and legal matters

No Comments

No Known Activations