INDEX

Explanations

text marked with a specific formatting element, represented by Ċ

oai_token-act-pair · gpt-3.5-turbo

sections of text related to academic citations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 diving

-0.71

 ideal

-0.71

 health

-0.66

 teammates

-0.66

 targets

-0.66

 frontline

-0.65

 volleyball

-0.64

 Horizon

-0.64

 vision

-0.63

 priority

-0.63

POSITIVE LOGITS

ÂłÂłÂłÂłÂłÂłÂłÂł

1.54

ÂłÂłÂł

1.50

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

1.44

ÂłÂłÂłÂł

1.38

Thus

1.30

posted

1.23

ÂłÂł

1.20

Conclusion

1.19

CONCLUS

1.19

Indeed

1.16

Activations Density 0.389%

text marked with a specific formatting element, represented by Ċ

sections of text related to academic citations and references

No Comments

No Known Activations