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

Loading

-0.73

PAC

-0.66

eki

-0.65

jet

-0.65

MX

-0.64

ctor

-0.61

 Fist

-0.61

 Might

-0.60

å£«

-0.60

ppo

-0.59

POSITIVE LOGITS

etheless

0.89

ishable

0.78

DragonMagazine

0.75

terday

0.70

soever

0.67

 redes

0.67

ĳå£«

0.62

 Rowling

0.62

 inver

0.62

idden

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.