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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undo

-0.76

ouf

-0.71

very

-0.68

enty

-0.66

any

-0.66

elong

-0.65

fair

-0.63

lore

-0.63

oos

-0.62

Champ

-0.61

POSITIVE LOGITS

 regard

1.11

 regards

1.10

stood

0.88

standing

0.87

 impunity

0.84

 caveats

0.82

ategory

0.73

 intent

0.72

 roomm

0.71

 respect

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.