INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

cart

-0.84

catentry

-0.84

itent

-0.83

icans

-0.81

atic

-0.78

ICAN

-0.78

saf

-0.78

-0.77

critical

-0.76

fire

-0.75

POSITIVE LOGITS

 millenn

0.70

 imperson

0.63

 Commons

0.62

 abst

0.61

rix

0.61

 slopes

0.60

 Reign

0.60

 verses

0.60

 straps

0.59

 Poss

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.