INDEX

Explanations

advice or instructions on productivity and personal development

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.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

guards

-0.75

 guards

-0.70

 latter

-0.69

 neighb

-0.66

 activ

-0.66

 ruled

-0.66

 valued

-0.65

 withd

-0.65

 union

-0.65

 behavi

-0.64

POSITIVE LOGITS

[+

1.27

 Conclusion

1.18

 Introduction

1.09

 Lack

0.92

 Thou

0.91

 CONTIN

0.88

 Learns

0.86

 Miscellaneous

0.85

 Recommend

0.85

 Ibid

0.84

Activations Density 0.709%

advice or instructions on productivity and personal development

No Comments

No Known Activations