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

 coron

-0.65

dinand

-0.65

cott

-0.62

 Buckingham

-0.61

rell

-0.61

Bib

-0.60

nell

-0.59

chin

-0.58

../

-0.58

conn

-0.58

POSITIVE LOGITS

âĹ¼

0.76

ãĥķãĤ©

0.68

ãĥķãĤ¡

0.68

yrim

0.67

 Peaks

0.67

ewski

0.66

 dracon

0.66

ItemTracker

0.65

ãĥ´ãĤ¡

0.65

 Ragnarok

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.