INDEX

Explanations

words in a different character encoding format

oai_token-act-pair · gpt-3.5-turbo

scss loving or preferring pleasant sensory experiences

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

 assignment

-0.79

 legally

-0.77

 unidentified

-0.73

 lawfully

-0.73

 bloc

-0.72

 intended

-0.71

 divest

-0.71

 probation

-0.71

 constitutionally

-0.70

 deceived

-0.69

POSITIVE LOGITS

Anyway

1.15

Advertisement

1.15

Conclusion

1.03

Luckily

0.99

Below

0.98

Thankfully

0.98

CONCLUS

0.98

Advertisements

0.97

Appearance

0.97

Favorite

0.97

Activations Density 0.536%

words in a different character encoding format

scss loving or preferring pleasant sensory experiences

No Comments

No Known Activations