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

egu

-0.72

orem

-0.71

antry

-0.69

iets

-0.69

ulhu

-0.67

 arise

-0.66

osure

-0.66

otomy

-0.65

izon

-0.65

================================================================

-0.63

POSITIVE LOGITS

ye

0.66

 Lent

0.64

Downloadha

0.63

 Johann

0.59

leaf

0.59

adobe

0.58

yo

0.58

tar

0.57

 Demand

0.56

 Kimberly

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.