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

Ò

-0.84

soDeliveryDate

-0.81

mia

-0.73

æĪ¦

-0.72

inventoryQuantity

-0.71

 Boxing

-0.68

 Denis

-0.68

ovych

-0.66

igan

-0.66

 Holden

-0.66

POSITIVE LOGITS

work

0.64

official

0.63

productive

0.62

voc

0.62

 legalize

0.61

udos

0.61

 exempted

0.61

 Authors

0.61

road

0.60

 tomat

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.