INDEX

Explanations

phrases related to giving instructions or providing information

oai_token-act-pair · gpt-3.5-turbo

elements related to personal experiences and reflections

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.","

-0.80

sed

-0.67

','

-0.62

arsity

-0.61

""

-0.59

ãĥı

-0.56

ãĥ´

-0.56

norm

-0.56

 âĢķ

-0.56

sen

-0.54

POSITIVE LOGITS

 Conclusion

1.32

 Lastly

1.30

Lastly

1.18

 concludes

1.10

 Finally

1.02

Finally

0.99

Conclusion

0.96

CONCLUS

0.95

 Summary

0.94

 concluding

0.93

Activations Density 0.414%

phrases related to giving instructions or providing information

elements related to personal experiences and reflections

No Comments

No Known Activations