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

 reinvest

-0.76

aii

-0.69

wed

-0.67

 clustered

-0.66

inous

-0.65

ework

-0.65

 rocked

-0.65

dom

-0.64

duct

-0.63

arded

-0.63

POSITIVE LOGITS

 Sass

0.77

ADA

0.75

 Tanks

0.75

 Zucker

0.73

swick

0.70

 Panzer

0.67

 Period

0.66

 Coulter

0.66

 Bugs

0.65

Sie

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.