INDEX

Explanations

mentions of the word "Nazi" or related terms

oai_token-act-pair · gpt-3.5-turbo

references to the Nazi regime and its associated concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Dub

-0.77

tis

-0.74

cially

-0.73

olulu

-0.72

WHERE

-0.71

changes

-0.69

Interstitial

-0.69

Asia

-0.68

area

-0.68

POSITIVE LOGITS

 Hitler

1.15

ocaust

1.11

chwitz

1.04

 Germany

0.99

 Holocaust

0.98

 Adolf

0.96

 Reich

0.96

 salute

0.94

 Nazi

0.93

 extermination

0.93

Activations Density 0.047%

mentions of the word "Nazi" or related terms

references to the Nazi regime and its associated concepts

No Comments

No Known Activations