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

yrim

-0.78

oute

-0.70

ase

-0.68

uli

-0.66

myra

-0.65

oleon

-0.63

lore

-0.62

 Koran

-0.62

acea

-0.62

icago

-0.62

POSITIVE LOGITS

 onward

0.67

ard

0.65

Acknowled

0.63

ctr

0.62

hement

0.62

hawks

0.61

taboola

0.60

SF

0.60

maxwell

0.60

sym

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.