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

idates

-0.83

ainer

-0.72

lio

-0.70

milo

-0.69

 Carbuncle

-0.68

 mathemat

-0.67

ency

-0.66

rity

-0.65

cerning

-0.65

lif

-0.64

POSITIVE LOGITS

 Rivals

0.70

Compare

0.66

FactoryReloaded

0.64

btn

0.62

 Cous

0.62

 stra

0.61

 Tradable

0.61

pmwiki

0.60

Sold

0.60

Dom

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.