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

enegger

-0.80

wald

-0.74

Nazis

-0.71

NN

-0.69

 ..."

-0.68

Ð´

-0.64

pread

-0.64

swick

-0.63

Nazi

-0.63

 criminality

-0.62

POSITIVE LOGITS

phis

0.82

rolet

0.73

phi

0.70

 EDIT

0.69

iciary

0.66

ctory

0.63

ero

0.63

mson

0.62

onis

0.62

voice

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.