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

encies

-0.76

ency

-0.72

arrell

-0.71

someone

-0.71

iterator

-0.68

itiveness

-0.66

Artist

-0.65

ourney

-0.64

 guiActiveUn

-0.63

itch

-0.63

POSITIVE LOGITS

 Thumbnails

0.75

 Happ

0.70

 Schn

0.69

skirts

0.67

 Schw

0.67

hest

0.65

 Ranch

0.64

alus

0.63

 Bills

0.62

LAT

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.