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

aturday

-0.91

Monday

-0.71

asper

-0.70

Tuesday

-0.69

nea

-0.68

MET

-0.67

aurus

-0.66

clipse

-0.65

Ore

-0.64

Amazon

-0.63

POSITIVE LOGITS

 vice

0.64

elsh

0.64

saf

0.62

FontSize

0.62

 UCHIJ

0.62

worldly

0.61

gel

0.61

AAAA

0.61

 arist

0.60

 incorpor

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.