INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Pens

-0.74

steen

-0.71

ictionary

-0.70

vation

-0.67

gain

-0.65

 Flavoring

-0.63

AZ

-0.63

 Reno

-0.62

isconsin

-0.62

kef

-0.61

POSITIVE LOGITS

 milit

0.70

hips

0.70

 Carbuncle

0.67

ander

0.67

ultane

0.63

anni

0.61

 footprint

0.60

tre

0.59

elsen

0.59

ishes

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.