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

 Sting

-0.78

 Honour

-0.76

 Assass

-0.70

 Honor

-0.69

 Uran

-0.67

Spy

-0.66

Cry

-0.66

 Wrest

-0.66

 Wasserman

-0.65

 Meow

-0.65

POSITIVE LOGITS

ashtra

0.74

»Ĵ

0.74

ãĥ³ãĤ¸

0.74

ĻĤ

0.73

roma

0.72

guyen

0.71

entimes

0.70

turned

0.70

ibaba

0.70

ŃĶ

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.