INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 prompts

-0.68

mentation

-0.68

 pupp

-0.67

 hotter

-0.67

 blush

-0.65

 kisses

-0.65

 sausage

-0.65

âĿ

-0.65

 registers

-0.65

 puppies

-0.63

POSITIVE LOGITS

Vision

0.70

 Gideon

0.67

ector

0.66

 Ultr

0.66

sis

0.63

achers

0.63

 Epidem

0.63

 Icar

0.63

 Confederation

0.63

 Foss

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.