INDEX

Explanations

references related to historical events, specifically the Holocaust

oai_token-act-pair · gpt-3.5-turbo

references to the Holocaust

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amina

-0.85

ateur

-0.82

gary

-0.76

uana

-0.73

ordinate

-0.72

semble

-0.71

tails

-0.70

idas

-0.69

ŃĶ

-0.68

ables

-0.66

POSITIVE LOGITS

ocaust

1.29

 Holocaust

1.20

 Remem

0.88

 Auschwitz

0.87

 Survivor

0.81

 Genocide

0.81

wald

0.80

 survivor

0.80

 survivors

0.79

 Pact

0.77

Activations Density 0.009%

references related to historical events, specifically the Holocaust

references to the Holocaust

No Comments

No Known Activations