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

 sober

-0.68

aurus

-0.68

oshop

-0.67

rift

-0.65

hire

-0.65

 sever

-0.65

lum

-0.65

 lodge

-0.64

woo

-0.64

estial

-0.63

POSITIVE LOGITS

 Previous

0.72

ersion

0.69

artifacts

0.67

adish

0.66

EStream

0.65

 Soldiers

0.65

 Cookies

0.62

dinand

0.62

EQU

0.61

 Athletics

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.