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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥİ

-0.70

imal

-0.68

enei

-0.66

%:

-0.65

hiro

-0.63

nil

-0.63

lee

-0.62

hib

-0.62

isal

-0.62

merga

-0.62

POSITIVE LOGITS

chen

0.69

 Doctrine

0.68

ebook

0.65

 Cros

0.65

ynthesis

0.63

 Weaver

0.63

 Wein

0.63

itcher

0.62

 Weber

0.62

ickr

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.