INDEX

Explanations

references to a specific location or entity, Puerto Rico

oai_token-act-pair · gpt-3.5-turbo

mentions of Puerto Rico

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

stroke

-0.74

GMT

-0.73

ister

-0.72

ä

-0.71

CHO

-0.69

onym

-0.69

points

-0.68

ISTER

-0.68

ä¹

-0.67

ãĥ¼ãĤ¯

-0.67

POSITIVE LOGITS

 Rico

1.40

 Rican

1.09

ricanes

0.86

 Unemployment

0.75

 Islands

0.75

 evac

0.71

 recovering

0.69

 flooded

0.68

 dwell

0.67

 FEMA

0.67

Activations Density 0.013%

references to a specific location or entity, Puerto Rico

mentions of Puerto Rico

No Comments

No Known Activations