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

ryu

-0.75

romeda

-0.74

entimes

-0.71

HE

-0.68

UTH

-0.66

Incre

-0.65

wcsstore

-0.64

ogg

-0.64

poon

-0.63

CLA

-0.62

POSITIVE LOGITS

 martial

0.85

 announcer

0.74

gamer

0.72

orer

0.71

 passer

0.70

jog

0.69

agers

0.69

 assassin

0.68

 actress

0.68

 referee

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.