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

dit

-0.80

 virt

-0.79

 Cron

-0.76

venant

-0.73

nen

-0.73

 recept

-0.71

voy

-0.68

rig

-0.68

rill

-0.68

ocket

-0.66

POSITIVE LOGITS

Ali

0.74

Products

0.67

)*

0.65

ĸļ

0.65

borg

0.64

ãĥĥãĥī

0.63

 Quantity

0.62

ô

0.62

multipl

0.61

:/

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.