INDEX

Explanations

instances where the word "In" is followed by some text

oai_token-act-pair · gpt-3.5-turbo

the end-of-text markers in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

.","

-0.69

','

-0.66

Ù

-0.63

swe

-0.61

 ..."

-0.61

.</

-0.61

 thereto

-0.61

='

-0.60

Ø

-0.60

""

-0.59

POSITIVE LOGITS

 Conclusion

1.24

 Lastly

0.99

notations

0.97

withstanding

0.93

endix

0.93

resa

0.90

odore

0.90

xon

0.89

ibliography

0.89

theless

0.87

Activations Density 0.500%

instances where the word "In" is followed by some text

the end-of-text markers in the document

No Comments

No Known Activations