INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Reason

-0.80

 Legislative

-0.73

 Citizen

-0.70

Veter

-0.67

ail

-0.67

 Veterans

-0.66

Mask

-0.65

âĢİ

-0.62

 Franchise

-0.62

 Unlock

-0.61

POSITIVE LOGITS

ullivan

0.74

utical

0.72

lda

0.69

ultane

0.67

 interchange

0.66

naissance

0.66

OTH

0.66

izont

0.66

zbollah

0.64

ucci

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.