INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

laim

-0.65

icz

-0.63

phal

-0.63

 Majesty

-0.62

und

-0.62

Nusra

-0.62

 Pradesh

-0.62

ight

-0.61

 Nadu

-0.61

Ã£

-0.61

POSITIVE LOGITS

rer

0.76

 Pres

0.67

Led

0.67

uras

0.65

ãĥĺãĥ©

0.65

 Sold

0.63

 Levin

0.63

aker

0.62

pert

0.61

 Moder

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.