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

 wart

-0.73

toe

-0.69

 invading

-0.68

 empires

-0.67

iamond

-0.65

 nations

-0.63

 harness

-0.61

 shifting

-0.58

 unchecked

-0.58

********

-0.58

POSITIVE LOGITS

TY

0.83

OSP

0.80

BILITIES

0.72

BILITY

0.71

atre

0.69

Bus

0.65

 BASE

0.65

APD

0.65

IPP

0.65

STD

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.