INDEX

Explanations

words related to military equipment or items such as numbers, weapon names and types, and other technical terms

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hement

-1.00

ĸļ

-0.83

ktop

-0.75

terday

-0.73

 agre

-0.73

ername

-0.73

nesday

-0.73

Ń·

-0.72

 aggressively

-0.72

 tremend

-0.70

POSITIVE LOGITS

ItemThumbnailImage

0.89

LESS

0.87

Conclusion

0.85

////////////////////////////////

0.85

--------------------------------------------------------

0.85

References

0.85

++++++++++++++++

0.84

Your

0.84

Using

0.83

Translation

0.82

Activations Density 0.616%

words related to military equipment or items such as numbers, weapon names and types, and other technical terms

numerical data or statistics

No Comments

No Known Activations