INDEX

Explanations

references to concentration camps, forced labor, and similar historical atrocities

oai_token-act-pair · gpt-3.5-turbo

references to historical atrocities and oppressive conditions, particularly related to concentration camps and forced labor

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

wcsstore

-0.87

 Toast

-0.84

 Prediction

-0.74

natureconservancy

-0.73

 Cary

-0.72

 Investors

-0.69

Shares

-0.68

 Prosper

-0.66

VP

-0.65

 Drivers

-0.64

POSITIVE LOGITS

 Auschwitz

1.20

 inmates

1.16

chwitz

1.15

 detainees

1.06

 confinement

0.99

 inmate

0.96

 prisoners

0.95

 barracks

0.95

 dehuman

0.91

gul

0.90

Activations Density 0.117%

references to concentration camps, forced labor, and similar historical atrocities

references to historical atrocities and oppressive conditions, particularly related to concentration camps and forced labor

No Comments

No Known Activations