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

eter

-0.80

entimes

-0.71

IPS

-0.70

 pauses

-0.62

Whe

-0.61

 Davies

-0.60

 reflections

-0.60

imaru

-0.60

isions

-0.59

 nodd

-0.59

POSITIVE LOGITS

 Mirage

0.68

 recharge

0.66

 upgrade

0.64

 upgr

0.64

prototype

0.63

alsa

0.63

luence

0.62

.","

0.62

Pwr

0.61

raped

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.