INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

bia

-0.80

idem

-0.80

fif

-0.70

è¦ļéĨĴ

-0.70

éĥ

-0.64

 Cosponsors

-0.63

fman

-0.63

bn

-0.61

ãĥ¼ãĥ

-0.61

alities

-0.61

POSITIVE LOGITS

Upload

0.68

Delivery

0.65

 uploaded

0.65

rus

0.63

Death

0.62

??

0.62

terday

0.60

 Cortana

0.59

ingen

0.59

ktop

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.