INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

çĶŁ

-0.74

ãģ®éŃĶ

-0.73

inventoryQuantity

-0.71

é¾įå¥ĳå£«

-0.67

ãĥ¯

-0.64

akening

-0.63

CR

-0.63

pload

-0.63

unia

-0.62

POSITIVE LOGITS

 Keane

0.74

 Categories

0.66

(@

0.62

dos

0.62

dra

0.60

 Draper

0.60

 Nuggets

0.59

 ðŁ

0.59

 Mavericks

0.59

makers

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.