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

anguage

-0.71

Files

-0.70

reads

-0.69

grain

-0.68

rams

-0.67

pointers

-0.66

awan

-0.66

igger

-0.66

ulia

-0.65

gars

-0.64

POSITIVE LOGITS

tical

0.70

 laughing

0.67

ucci

0.66

TBD

0.66

 ç¥ŀ

0.63

 ÃĹ

0.62

ãĥŃ

0.60

Os

0.60

SOC

0.59

EG

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.