INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

UX

-0.84

stakes

-0.72

lished

-0.71

ointed

-0.70

aries

-0.70

het

-0.68

ighters

-0.67

hani

-0.67

llo

-0.67

ubs

-0.66

POSITIVE LOGITS

 schizophrenia

0.75

ecd

0.70

 conscientious

0.65

 maternal

0.64

 migraine

0.62

 schizophren

0.62

hawk

0.62

 prenatal

0.62

uyomi

0.62

 adolescent

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.