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

¬¼

-0.88

 è£ıè

-0.80

lehem

-0.79

BuyableInstoreAndOnline

-0.77

ÙĴ

-0.76

 Pixie

-0.73

 mascara

-0.73

âĶģ

-0.72

 Notting

-0.72

-+-+

-0.71

POSITIVE LOGITS

appers

0.72

osponsors

0.69

utt

0.67

eem

0.67

ographers

0.65

pard

0.63

abor

0.62

osa

0.62

antha

0.62

otes

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.