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

 trillions

-0.75

 Mubarak

-0.71

 Gujarat

-0.68

ãĢĳ

-0.68

Í

-0.68

 Uttar

-0.67

é¾

-0.67

.–

-0.66

 Grassley

-0.66

=]

-0.66

POSITIVE LOGITS

glers

0.86

anson

0.75

uctor

0.73

©¶æ

0.70

 interior

0.65

 Plot

0.65

adem

0.63

erion

0.63

itute

0.63

uther

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.