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

iqueness

-0.75

ersen

-0.68

 posture

-0.64

untu

-0.63

nen

-0.62

indal

-0.60

gaard

-0.58

isconsin

-0.58

endon

-0.57

lopp

-0.57

POSITIVE LOGITS

aph

0.75

utor

0.71

xx

0.68

 Turtle

0.67

Ir

0.66

glers

0.65

hes

0.64

cised

0.64

Scar

0.64

 amalg

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.