INDEX

Explanations

No Explanations Found

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

 Orient

-0.73

 Regions

-0.67

Russ

-0.67

olitics

-0.67

avid

-0.65

daq

-0.65

Lon

-0.62

 Danger

-0.62

UTC

-0.61

 Russ

-0.60

POSITIVE LOGITS

 cape

0.68

package

0.67

berman

0.67

bat

0.64

 boiler

0.63

 encaps

0.63

 intest

0.63

ãĤ¡

0.62

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

0.61

 nursery

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.