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

enture

-0.77

worms

-0.65

insk

-0.64

 Bret

-0.64

 Corm

-0.63

 Football

-0.63

CHAT

-0.63

mination

-0.63

 Colombia

-0.62

Jav

-0.62

POSITIVE LOGITS

semb

0.75

sylv

0.71

yout

0.69

rev

0.68

det

0.67

roud

0.65

universal

0.64

edition

0.62

alm

0.62

 disg

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.