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

SPONSORED

-0.75

ussen

-0.70

yre

-0.64

 thereof

-0.63

 âĢ¦

-0.61

 Lisbon

-0.59

 IMAGES

-0.58

 whence

-0.58

 highways

-0.58

 Hebdo

-0.56

POSITIVE LOGITS

0.81

bows

0.71

Bed

0.71

PF

0.70

Ish

0.68

Found

0.68

bow

0.65

\\\\\\\\

0.65

robe

0.65

leigh

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.