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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orem

-0.69

 confir

-0.69

atform

-0.68

ÃĥÃĤ

-0.67

chwitz

-0.65

onut

-0.65

adena

-0.63

omon

-0.63

 Runs

-0.62

omo

-0.62

POSITIVE LOGITS

ç·

0.79

ä½¿

0.71

Bright

0.70

çļ

0.70

Ing

0.70

å¤

0.68

çī

0.68

é£

0.68

 Asus

0.66

 Hamp

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.