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

 actionGroup

-0.86

intendent

-0.77

ournals

-0.73

icio

-0.71

sd

-0.68

sis

-0.66

itri

-0.66

eways

-0.65

 dilig

-0.65

 teasp

-0.64

POSITIVE LOGITS

 renown

0.68

 Flesh

0.67

Lau

0.65

 Schne

0.65

ulia

0.64

 Valkyrie

0.63

 Cheong

0.63

ÄŁ

0.62

 Revel

0.60

 giveaway

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.