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

imate

-0.67

inches

-0.67

 condu

-0.65

actus

-0.62

utter

-0.62

imes

-0.61

abs

-0.61

illin

-0.60

unin

-0.58

æ©

-0.58

POSITIVE LOGITS

sic

0.74

soever

0.74

atility

0.71

 Else

0.68

bek

0.67

ãĥĦ

0.66

wagen

0.64

ieval

0.64

 Purg

0.64

 Haram

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.