INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

èĢħ

-0.83

Apart

-0.77

imental

-0.77

Bank

-0.74

ATA

-0.73

EMS

-0.71

ALS

-0.68

STEM

-0.67

BuyableInstoreAndOnline

-0.67

 Morales

-0.66

POSITIVE LOGITS

İĭ

0.79

hovah

0.75

 fert

0.74

 elig

0.73

 volunte

0.71

 gobl

0.69

 spawning

0.69

 vets

0.68

zeb

0.68

 ancest

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.