INDEX

Explanations

meaningful sentences with a strong emphasis or conclusion at the end

oai_token-act-pair · gpt-3.5-turbo

periods at the end of sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 behavi

-0.73

 administrator

-0.69

 independ

-0.68

 valued

-0.68

 rule

-0.66

 overlooked

-0.64

 activ

-0.63

 underestimated

-0.63

 renters

-0.62

 neglected

-0.62

POSITIVE LOGITS

 Learns

0.97

[+

0.95

 Ibid

0.86

jar

0.85

 Whilst

0.85

 Conclusion

0.83

 Lack

0.82

jpg

0.81

 ISBN

0.81

htm

0.80

Activations Density 0.059%

meaningful sentences with a strong emphasis or conclusion at the end

periods at the end of sentences

No Comments

No Known Activations