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

}}}

-0.76

uring

-0.74

emaker

-0.70

orno

-0.68

ocene

-0.67

 dates

-0.65

+#

-0.64

 chars

-0.63

elaide

-0.62

adish

-0.61

POSITIVE LOGITS

 kinderg

0.69

south

0.69

Sof

0.68

Front

0.66

brother

0.66

alsh

0.65

 pupils

0.63

founded

0.62

dinand

0.62

indal

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.