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

idential

-0.76

ubb

-0.74

SPONSORED

-0.72

orr

-0.72

ipher

-0.70

APD

-0.70

natureconservancy

-0.68

arcer

-0.68

unin

-0.67

oult

-0.66

POSITIVE LOGITS

Tav

0.67

Jane

0.67

 Simone

0.67

 resume

0.66

 Feel

0.66

Vaj

0.66

 Jane

0.65

beit

0.65

 Madonna

0.64

 McMaster

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.