INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

aroo

-0.46

abama

-0.44

izers

-0.42

 Session

-0.40

fund

-0.40

une

-0.38

vik

-0.38

hop

-0.37

pee

-0.37

adders

-0.37

POSITIVE LOGITS

udence

0.44

endez

0.40

æŃ

0.39

kefeller

0.39

Ley

0.38

 Shinra

0.38

 concess

0.37

Saharan

0.36

bats

0.36

 Yose

0.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.