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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

requ

-0.70

otrop

-0.69

olit

-0.67

abases

-0.65

 Olymp

-0.63

olitics

-0.63

MW

-0.62

urga

-0.62

 Katy

-0.61

CFL

-0.60

POSITIVE LOGITS

 Rooms

0.82

hov

0.77

boys

0.68

 Slime

0.67

ãĤ©

0.65

ennes

0.64

 Mansion

0.61

lia

0.61

 Colour

0.60

holiday

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.