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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 isot

-0.71

irl

-0.71

peria

-0.67

Iraq

-0.62

qqa

-0.62

 Sana

-0.62

ova

-0.61

vet

-0.59

 Beirut

-0.59

omnia

-0.58

POSITIVE LOGITS

ango

0.83

 bribe

0.66

âĸĴ

0.66

âĸĵ

0.66

pling

0.64

 Kits

0.64

 Curve

0.63

FFFF

0.61

Mouse

0.60

ixel

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.