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

 Rampage

-0.79

ocry

-0.77

 Xperia

-0.76

 Gauntlet

-0.73

 Rico

-0.73

 Rivals

-0.71

.ï¿½

-0.70

ãģ®æ

-0.70

Oro

-0.69

 Cobra

-0.67

POSITIVE LOGITS

avascript

0.79

chal

0.73

byn

0.72

tel

0.69

scill

0.69

Pg

0.68

rocal

0.67

spr

0.65

pit

0.65

acial

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.