INDEX

Explanations

proper nouns denoting nationalities

oai_token-act-pair · gpt-3.5-turbo

mentions of specific nationalities or ethnic groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.74

utherford

-0.69

efer

-0.67

scape

-0.65

miss

-0.65

 Tulsa

-0.65

 McDonnell

-0.64

ounty

-0.64

ãĥ¼ãĥ³

-0.64

Seattle

-0.64

POSITIVE LOGITS

aurus

0.91

who

0.90

paces

0.86

ourced

0.78

 living

0.75

ango

0.75

0.74

 residing

0.73

istani

0.73

ians

0.72

Activations Density 0.069%

proper nouns denoting nationalities

mentions of specific nationalities or ethnic groups

No Comments

No Known Activations