INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 partName

-0.86

soType

-0.80

ãĤµ

-0.79

ãĤ´ãĥ³

-0.78

actionDate

-0.76

udeb

-0.74

DragonMagazine

-0.71

ERROR

-0.70

ħĭ

-0.68

Gaza

-0.68

POSITIVE LOGITS

akin

0.64

aints

0.64

soever

0.63

 penalties

0.62

 virtues

0.61

 Combine

0.61

eton

0.60

ry

0.60

 Saints

0.59

 Panthers

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.