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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

manship

-0.71

appa

-0.71

-0.70

-0.69

--------------------------------------------------------

-0.68

taboola

-0.68

lessness

-0.67

chenko

-0.65

nikov

-0.65

 eject

-0.64

POSITIVE LOGITS

 ends

1.26

 Ends

0.92

 Bind

0.71

 Slot

0.69

Slot

0.68

 Isle

0.67

 Zeit

0.65

 Hispan

0.64

 Negro

0.64

 Bunny

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.