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

bryce

-0.86

natureconservancy

-0.70

DragonMagazine

-0.68

ROM

-0.67

cry

-0.65

lot

-0.64

wal

-0.63

mir

-0.63

````

-0.62

POSITIVE LOGITS

 aver

0.76

ocide

0.64

iciency

0.63

 plaus

0.63

atever

0.62

 Arabs

0.62

 Consumption

0.62

 unspecified

0.61

 Caucas

0.60

rame

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.