INDEX

Explanations

terms related to historical events, particularly focusing on the Holocaust

oai_token-act-pair · gpt-3.5-turbo

references to the Holocaust and related themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

amina

-0.87

ateur

-0.82

ordinate

-0.75

semble

-0.72

ths

-0.70

erd

-0.69

tails

-0.68

gary

-0.68

uana

-0.67

idas

-0.66

POSITIVE LOGITS

ocaust

1.22

 Holocaust

1.18

 Auschwitz

0.86

 Survivor

0.85

 survivor

0.84

wald

0.78

 Genocide

0.78

 survivors

0.78

 Remem

0.78

 Zombies

0.75

Activations Density 0.007%

terms related to historical events, particularly focusing on the Holocaust

references to the Holocaust and related themes

No Comments

No Known Activations