INDEX

Explanations

technical terms related to software development and quality assurance

oai_token-act-pair · gpt-3.5-turbo

phrases indicating additional features or capabilities

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

Negative Logits

.</

-0.70

—"

-0.67

.''

-0.64

 hers

-0.61

 ÂŃ

-0.59

 âĢķ

-0.57

Putin

-0.57

 thereof

-0.57

 afterward

-0.57

 thereto

-0.57

POSITIVE LOGITS

 Conclusion

0.80

ktop

0.72

 Background

0.69

Â¶

0.69

 Edit

0.68

isks

0.67

 Lets

0.67

 disclaimer

0.66

 Tutorial

0.65

ynchronous

0.65

Activations Density 1.300%

technical terms related to software development and quality assurance

phrases indicating additional features or capabilities

No Known Activations