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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thumbnails

-0.70

EO

-0.66

GH

-0.64

Zap

-0.64

imony

-0.62

 glasses

-0.62

ãĤ¹ãĥĪ

-0.60

Sut

-0.60

skirts

-0.58

ricks

-0.58

POSITIVE LOGITS

 incub

0.67

 ancest

0.67

 notor

0.67

nesota

0.66

abase

0.65

 antim

0.64

ername

0.64

 assassin

0.63

alian

0.63

asus

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.