INDEX

Explanations

Biblical references

oai_token-act-pair · gpt-3.5-turbo

phrases indicating moral or ethical judgments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 trending

-0.88

 snowball

-0.85

 transitioning

-0.84

 takeaway

-0.84

 impacted

-0.83

 fallout

-0.83

 coordinated

-0.83

 babys

-0.83

 targeted

-0.83

 proactive

-0.82

POSITIVE LOGITS

CHAPTER

1.45

 Accordingly

1.35

 Hence

1.35

 Thus

1.35

 Suppose

1.34

Thus

1.25

Cf

1.20

 Such

1.18

 Notwithstanding

1.18

Chapter

1.16

Activations Density 0.433%

Biblical references

phrases indicating moral or ethical judgments

No Comments

No Known Activations