INDEX

Explanations

mentions of detention centers or facilities

oai_token-act-pair · gpt-3.5-turbo

references to detention facilities and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

soDeliveryDate

-0.72

ãĥ£

-0.70

bold

-0.66

 PsyNet

-0.66

wb

-0.66

shadow

-0.65

ced

-0.65

Roll

-0.63

ider

-0.62

clerosis

-0.61

POSITIVE LOGITS

 detention

1.07

rooms

0.91

 facilities

0.88

 detainees

0.83

 confinement

0.83

 camps

0.81

 Facility

0.80

 detain

0.79

 centers

0.77

 centres

0.76

Activations Density 0.017%

mentions of detention centers or facilities

references to detention facilities and related concepts

No Comments

No Known Activations