INDEX

Explanations

specific symbols

oai_token-act-pair · gpt-3.5-turbo

instances of numerical values or counts in the text

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

 thrill

-0.78

 neighb

-0.77

 knockout

-0.76

 lifes

-0.75

 slam

-0.73

 spitting

-0.73

 wrapped

-0.72

 grip

-0.72

 agon

-0.71

 casc

-0.70

POSITIVE LOGITS

Additionally

1.50

However

1.48

References

1.43

Furthermore

1.43

Conclusion

1.42

Below

1.41

Therefore

1.39

Using

1.39

Generally

1.39

Although

1.38

Activations Density 0.419%

specific symbols

instances of numerical values or counts in the text

No Comments

No Known Activations