INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ommod

-0.78

chron

-0.76

PsyNetMessage

-0.72

 describ

-0.71

eworld

-0.69

DragonMagazine

-0.67

Joined

-0.66

 IMAGES

-0.66

geries

-0.66

esses

-0.64

POSITIVE LOGITS

ħĭ

0.84

 Flavoring

0.77

leans

0.74

CoC

0.71

 ratios

0.67

 cough

0.67

ļéĨĴ

0.64

 coconut

0.64

 opioids

0.64

scl

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.