INDEX

Explanations

references to Jews and anti-Semitic content

oai_token-act-pair · gpt-3.5-turbo

references to Jewish identity and experiences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inventoryQuantity

-0.83

URRENT

-0.77

ctive

-0.74

shown

-0.71

tnc

-0.69

nant

-0.68

amina

-0.67

ISTER

-0.67

cer

-0.67

NRS

-0.67

POSITIVE LOGITS

 Jews

0.93

 Israelis

0.87

geist

0.85

ellery

0.84

ophobia

0.77

esses

0.74

 Arabs

0.73

odus

0.73

 Juda

0.73

Semitism

0.73

Activations Density 0.008%

references to Jews and anti-Semitic content

references to Jewish identity and experiences

No Comments

No Known Activations