INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

byter

-0.78

lycer

-0.74

guard

-0.67

wav

-0.67

 PowerPoint

-0.65

TF

-0.64

Newsletter

-0.61

past

-0.61

ART

-0.61

NA

-0.60

POSITIVE LOGITS

 Giuliani

0.70

 Deluxe

0.69

 Echoes

0.69

ugi

0.67

iability

0.66

 Pluto

0.65

cla

0.65

 Osiris

0.64

 Interstellar

0.63

 liter

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.