INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

[&

-0.73

Construction

-0.71

Mayor

-0.71

mails

-0.70

heny

-0.70

cffffcc

-0.68

DonaldTrump

-0.66

Education

-0.66

Critical

-0.65

Hidden

-0.65

POSITIVE LOGITS

amina

0.75

 aggress

0.71

OY

0.68

amera

0.66

©¶æ

0.66

itten

0.64

 covering

0.64

owered

0.64

urnal

0.63

itialized

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.