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

enance

-0.83

anova

-0.71

SHIP

-0.71

 Mirage

-0.67

urat

-0.66

life

-0.65

luster

-0.65

shine

-0.64

nice

-0.63

bird

-0.63

POSITIVE LOGITS

TPS

0.80

 WATCHED

0.73

ä¼

0.71

à¼

0.70

ould

0.68

taboola

0.65

ĨĴ

0.64

0.61

otin

0.60

 dissemin

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.