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

 Gujarat

-0.80

 Majesty

-0.78

 Gujar

-0.77

 Shah

-0.77

assy

-0.75

adh

-0.74

 Uttar

-0.72

 Chennai

-0.72

ilee

-0.72

 Kerala

-0.72

POSITIVE LOGITS

å§«

0.71

iasco

0.70

cyclopedia

0.67

urtles

0.66

zynski

0.65

ħĭ

0.65

milo

0.64

 stripes

0.62

ĻĤ

0.62

 Matter

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.