INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

terday

-0.78

 Fisheries

-0.71

 Places

-0.71

 Parameters

-0.71

theless

-0.67

 Tire

-0.65

 mathemat

-0.64

params

-0.63

 parameters

-0.62

 accur

-0.62

POSITIVE LOGITS

rored

0.67

OU

0.67

erto

0.67

weet

0.67

NT

0.66

 entit

0.65

 healthy

0.64

 Shutterstock

0.63

uate

0.62

icol

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.