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

alogue

-0.69

opa

-0.68

Ãº

-0.66

 coloured

-0.66

arity

-0.66

 Soup

-0.65

phans

-0.65

 newcom

-0.64

amped

-0.63

Shell

-0.63

POSITIVE LOGITS

 Skydragon

0.74

Adds

0.70

arro

0.67

 Rossi

0.66

 Strauss

0.64

¶ħ

0.64

cock

0.64

 Whedon

0.62

 Gork

0.61

amide

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.