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

ONY

-0.79

acea

-0.75

TON

-0.70

important

-0.69

>[

-0.66

ANA

-0.66

hani

-0.65

+.

-0.65

BRE

-0.64

\<

-0.63

POSITIVE LOGITS

raints

0.80

umes

0.67

 constraints

0.66

ricular

0.65

 channels

0.63

 eject

0.63

wich

0.63

 virginity

0.63

 Mandarin

0.62

 decriminal

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.