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

 helicop

-0.76

 hacks

-0.70

bern

-0.70

 drip

-0.69

 notor

-0.64

 graft

-0.63

 tram

-0.62

 mang

-0.62

rul

-0.62

 Leban

-0.62

POSITIVE LOGITS

Time

0.79

Timer

0.71

Fi

0.70

ittal

0.70

 time

0.69

Final

0.69

 Time

0.68

jan

0.67

nutrition

0.67

 Ples

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.