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

ploma

-0.68

ician

-0.67

bye

-0.67

Andy

-0.65

enburg

-0.63

rolog

-0.63

ntil

-0.62

opl

-0.60

Daddy

-0.60

ģĸ

-0.59

POSITIVE LOGITS

xual

0.77

ciation

0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.63

":["

0.62

 Properties

0.62

SPONSORED

0.62

 Reflex

0.58

aturated

0.58

?ãĢį

0.58

hov

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.