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

ramid

-1.04

uilt

-0.89

ortium

-0.89

eanor

-0.87

alach

-0.84

artisan

-0.81

ouk

-0.79

ounty

-0.79

VIDIA

-0.76

ottage

-0.75

POSITIVE LOGITS

CIS

0.82

 consuming

0.78

 passing

0.72

 Zucker

0.67

aneously

0.67

 frame

0.65

frames

0.65

 inacc

0.65

 relying

0.65

 regards

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.