INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

abal

-0.72

 borrow

-0.70

apse

-0.70

 fractures

-0.70

 bleed

-0.68

ipel

-0.68

erella

-0.67

afa

-0.66

 flares

-0.65

robat

-0.64

POSITIVE LOGITS

LEY

0.73

 intelligence

0.66

tips

0.63

HUM

0.63

STON

0.63

advertising

0.62

 Networks

0.62

INESS

0.61

spoken

0.61

stead

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.