INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 thief

-0.66

 floods

-0.66

 oxide

-0.63

 burg

-0.62

coat

-0.61

 diffusion

-0.61

 hacks

-0.61

 stray

-0.61

 happ

-0.61

 pirate

-0.61

POSITIVE LOGITS

ï¸

0.83

rolet

0.70

]"

0.69

×Ķ

0.68

rogen

0.66

phasis

0.66

plet

0.66

hler

0.65

rica

0.63

 Doctrine

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.