INDEX

Explanations

references related to historical events, particularly focusing on the Holocaust

oai_token-act-pair · gpt-3.5-turbo

references to the Holocaust and related topics

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

ateur

-0.89

amina

-0.81

tails

-0.78

uana

-0.77

ŃĶ

-0.74

gary

-0.68

 mates

-0.68

semble

-0.68

gap

-0.68

ordinate

-0.67

POSITIVE LOGITS

ocaust

1.22

 Holocaust

1.06

 Remem

0.90

 Genocide

0.81

 survivor

0.79

 survivors

0.78

 Crisis

0.77

 Memorial

0.77

wald

0.76

den

0.76

Activations Density 0.024%

references related to historical events, particularly focusing on the Holocaust

references to the Holocaust and related topics

No Comments

No Known Activations