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

otte

-0.82

ottest

-0.75

anche

-0.75

 declares

-0.68

anos

-0.66

hunt

-0.66

tes

-0.65

 executes

-0.63

rates

-0.61

afia

-0.61

POSITIVE LOGITS

 Parables

0.76

 ILCS

0.71

é»Ĵ

0.71

 fuse

0.71

 Notting

0.70

Ô

0.70

Portland

0.69

SCP

0.67

LU

0.66

arthed

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.