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

chuk

-0.79

tsky

-0.73

quickShipAvailable

-0.69

weed

-0.69

SpaceEngineers

-0.68

MpServer

-0.67

otin

-0.65

atural

-0.65

IAS

-0.65

FTWARE

-0.65

POSITIVE LOGITS

adder

0.63

uf

0.62

****************

0.62

ãĤ¼

0.60

 Card

0.60

Els

0.60

Card

0.58

 Sack

0.58

 Madd

0.57

*)

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.