INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

arters

-0.79

eve

-0.72

ients

-0.70

agents

-0.68

 Benson

-0.68

ainers

-0.68

fixes

-0.67

mson

-0.67

EV

-0.66

baugh

-0.65

POSITIVE LOGITS

 vulner

0.75

cu

0.67

>[

0.65

 garment

0.64

eton

0.63

 myster

0.62

 Tweet

0.62

cu

0.60

vention

0.60

 poised

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.