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

zar

-0.75

gomery

-0.68

udo

-0.66

icer

-0.66

hor

-0.65

Square

-0.65

rative

-0.65

ungle

-0.65

hover

-0.63

Bot

-0.63

POSITIVE LOGITS

ITNESS

0.73

ĪĴ

0.67

avis

0.67

steel

0.66

Ò

0.64

 breathe

0.62

rogens

0.61

 breath

0.61

 Helsinki

0.59

razil

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.