INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ufact

-0.70

 mileage

-0.63

 lobb

-0.62

andise

-0.62

uez

-0.62

chnology

-0.61

 gear

-0.60

oward

-0.60

throp

-0.59

 Coffin

-0.58

POSITIVE LOGITS

ADRA

0.79

ailable

0.77

Reviewer

0.75

Ħ¢

0.69

agus

0.69

HCR

0.67

atican

0.66

 Blaz

0.66

formed

0.66

Prosecut

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.