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

²¾

-0.78

ĸļ

-0.68

»Ĵ

-0.67

ktop

-0.66

 Antar

-0.64

ĥ

-0.63

 Reconstruction

-0.61

 Millennials

-0.60

 Ãľ

-0.60

 Virtue

-0.60

POSITIVE LOGITS

orks

0.76

til

0.70

ragon

0.70

worth

0.68

idge

0.68

til

0.67

arde

0.66

<-

0.66

racuse

0.66

ear

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.