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

 extraord

-0.71

afety

-0.70

 laps

-0.69

ãĤ§

-0.68

aucus

-0.65

UME

-0.64

"]=>

-0.63

matter

-0.63

perature

-0.62

è¯

-0.62

POSITIVE LOGITS

kees

0.77

 Yamato

0.70

Kun

0.67

kin

0.65

avorite

0.63

asin

0.62

seed

0.61

Lago

0.60

inski

0.60

kov

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.