INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

umption

-0.75

 Labor

-0.66

 Prel

-0.66

prof

-0.65

 Meat

-0.64

 Wine

-0.62

 Quarter

-0.61

jp

-0.60

 Beef

-0.58

 Chrom

-0.58

POSITIVE LOGITS

ModLoader

0.81

QUI

0.74

IVER

0.74

pmwiki

0.74

aukee

0.72

ãĥ¼ãĥĨãĤ£

0.72

maxwell

0.71

DAQ

0.71

ãĤ§

0.70

ļéĨĴ

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.