INDEX

Explanations

No Explanations Found

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

amera

-0.72

################################

-0.70

aring

-0.69

ItemImage

-0.68

kees

-0.67

athered

-0.66

onew

-0.66

inventoryQuantity

-0.66

}}}

-0.66

uana

-0.63

POSITIVE LOGITS

iannopoulos

0.68

 UNESCO

0.64

enegger

0.62

billion

0.61

 Canterbury

0.60

Nou

0.60

ãĥĲ

0.60

ournal

0.60

 Bhar

0.60

 Lara

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.