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

Operation

-0.72

ldom

-0.69

oufl

-0.69

âĶ

-0.68

onyms

-0.68

isf

-0.68

\\\\\\\\

-0.67

ports

-0.66

å¦

-0.65

ãħĭ

-0.64

POSITIVE LOGITS

Vie

0.66

Phys

0.65

Ket

0.65

Pam

0.63

Rez

0.63

Cec

0.62

 Applic

0.62

iaz

0.62

Dak

0.62

 Sequ

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.