INDEX

Explanations

unsafe or dangerous situations or conditions

oai_token-act-pair · gpt-3.5-turbo

references to safety and conditions deemed unsafe

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

frey

-0.86

braska

-0.84

orah

-0.83

yss

-0.82

issance

-0.81

ership

-0.80

hunt

-0.80

gdala

-0.79

cence

-0.78

anche

-0.77

POSITIVE LOGITS

 unsafe

1.10

 safe

0.73

 adolesc

0.73

Ez

0.68

 hazardous

0.68

Msg

0.64

 Safe

0.64

 paste

0.63

NESS

0.63

 risky

0.62

Activations Density 0.007%

unsafe or dangerous situations or conditions

references to safety and conditions deemed unsafe

No Comments

No Known Activations