INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

OPLE

-0.81

è¦ļéĨĴ

-0.73

ople

-0.70

Args

-0.66

iens

-0.65

[|

-0.64

iversity

-0.63

tnc

-0.63

 Template

-0.63

classes

-0.63

POSITIVE LOGITS

ndra

0.76

ahn

0.69

rish

0.69

Pwr

0.69

gypt

0.68

weet

0.68

andi

0.67

pring

0.66

oshi

0.66

ela

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.