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

Negative Logits

 Imran

-0.67

Ik

-0.64

ãĤĬ

-0.63

skip

-0.62

 curs

-0.62

 Stretch

-0.61

 Phant

-0.61

 Taiwanese

-0.58

Qi

-0.58

 Dolphin

-0.58

POSITIVE LOGITS

affer

0.83

minecraft

0.81

ariat

0.75

ayer

0.73

Score

0.69

usat

0.68

Magn

0.68

FML

0.68

Berry

0.65

Win

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.