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

natureconservancy

-0.83

iscons

-0.78

ruciating

-0.69

eur

-0.67

clerosis

-0.66

ichita

-0.66

iet

-0.63

ateur

-0.62

ulner

-0.62

 Nadu

-0.61

POSITIVE LOGITS

abal

0.99

 Starr

0.70

SpaceEngineers

0.69

 prompt

0.63

 perme

0.62

 yours

0.62

 timely

0.62

 completion

0.59

 Fract

0.59

Ãį

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.