INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

sonian

-0.89

imar

-0.79

ãĥ¼ãĥĨãĤ£

-0.79

Vi

-0.70

imum

-0.69

 Mehran

-0.67

nil

-0.67

uyomi

-0.66

chwitz

-0.66

 necks

-0.66

POSITIVE LOGITS

alling

0.79

rant

0.73

 Droid

0.73

amins

0.71

 Kindle

0.71

antics

0.69

ffe

0.68

wing

0.65

 Galaxy

0.65

 Butterfly

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.