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

oulos

-0.81

abba

-0.69

raltar

-0.67

 Skydragon

-0.67

edia

-0.63

aeda

-0.62

ļéĨĴ

-0.61

 "$:/

-0.61

 Gorge

-0.61

 Levant

-0.60

POSITIVE LOGITS

 BALL

0.73

through

0.69

ograph

0.65

rod

0.63

osite

0.62

ball

0.61

draft

0.61

rike

0.61

frog

0.61

 constitu

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.