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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

osi

-0.81

arching

-0.74

arth

-0.73

iday

-0.72

perty

-0.70

uron

-0.70

elson

-0.69

onia

-0.69

ornings

-0.67

nor

-0.67

POSITIVE LOGITS

 Contrast

0.69

vertisement

0.68

deals

0.67

 DEBUG

0.64

AVG

0.63

 Uncharted

0.63

\\\\\\\\\\\\\\\\

0.63

 playbook

0.62

 Traps

0.62

TPP

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.