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

landers

-0.73

zyme

-0.70

atchewan

-0.63

ructose

-0.63

rero

-0.63

PF

-0.63

ĨĴ

-0.63

 Burton

-0.62

 Javascript

-0.62

asio

-0.62

POSITIVE LOGITS

thel

0.71

CET

0.65

oft

0.65

0.60

thro

0.58

 prepar

0.58

cms

0.58

ä¹ĭ

0.58

ocent

0.58

 advocating

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.