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

mares

-0.96

RTX

-0.88

xes

-0.77

containing

-0.72

acio

-0.72

ECD

-0.72

ornia

-0.72

ORN

-0.71

ãĥĺãĥ©

-0.70

itely

-0.69

POSITIVE LOGITS

 hacks

0.76

 Wife

0.73

 banker

0.72

 meter

0.70

"]=>

0.67

 screws

0.65

orgetown

0.64

 backdrop

0.64

 hinge

0.64

 anchors

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.