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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INESS

-0.81

 rotting

-0.65

 ashes

-0.62

è¦ļéĨĴ

-0.61

 Lexington

-0.61

OUP

-0.60

 DeVos

-0.60

Russ

-0.59

 Omaha

-0.59

 violet

-0.59

POSITIVE LOGITS

jing

0.85

rotein

0.75

phabet

0.75

uploads

0.74

aments

0.67

mology

0.67

ouf

0.67

ht

0.65

Jed

0.65

orius

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.