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

oids

-0.72

aband

-0.68

cha

-0.66

 surpr

-0.66

 majorities

-0.66

 cheers

-0.65

iments

-0.65

 Cohn

-0.64

Meta

-0.63

 Feinstein

-0.63

POSITIVE LOGITS

 Reborn

0.82

 Lumin

0.72

rift

0.71

arist

0.70

RD

0.67

worker

0.67

yna

0.67

 McKay

0.66

 Wedding

0.66

 Phot

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.