INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Lauder

-0.82

ãĢı

-0.76

 Beir

-0.71

?????-

-0.67

?????-?????-

-0.67

 resil

-0.67

 Nadu

-0.65

eq

-0.65

ãĥ£

-0.64

ikuman

-0.62

POSITIVE LOGITS

gers

0.85

kies

0.76

weed

0.71

mouth

0.65

keyes

0.64

olls

0.64

ange

0.63

isco

0.62

etsy

0.60

orts

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.