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

 Forsaken

-0.75

 liner

-0.73

 Liter

-0.69

éĹ

-0.69

è£

-0.69

itialized

-0.69

 EntityItem

-0.68

Creat

-0.65

 Univers

-0.65

 Fract

-0.65

POSITIVE LOGITS

mons

0.78

yss

0.78

emate

0.77

ikarp

0.76

 Klux

0.70

aukee

0.70

utz

0.70

Gay

0.68

mia

0.68

otiation

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.