INDEX

Explanations

mentions of or references to prisons

oai_token-act-pair · gpt-3.5-turbo

references to prisons and jails

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

uin

-0.70

stall

-0.68

set

-0.66

ainer

-0.66

 piece

-0.66

link

-0.62

 Item

-0.59

 brand

-0.58

 item

-0.58

 team

-0.58

POSITIVE LOGITS

 prisons

3.64

 jails

2.92

 prisoners

1.65

 hospitals

1.59

 correctional

1.56

 stadiums

1.51

 prison

1.48

 warehouses

1.48

 inmates

1.47

 universities

1.46

Activations Density 0.012%

mentions of or references to prisons

references to prisons and jails

No Comments

No Known Activations