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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pport

-0.72

nect

-0.72

apult

-0.70

thood

-0.68

erate

-0.67

oons

-0.66

akedown

-0.65

iso

-0.65

ula

-0.65

itivity

-0.64

POSITIVE LOGITS

Course

0.79

WAR

0.73

leigh

0.67

Posted

0.67

 contrary

0.66

Absolutely

0.66

Relations

0.65

killed

0.64

CRE

0.63

Hit

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.