INDEX

Explanations

information about a person's medical treatment, particularly related to being transported to hospitals for treatment and release

oai_token-act-pair · gpt-3.5-turbo

phrases related to medical treatment and recovery events

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

 sensit

-0.56

 Nielsen

-0.56

 acronym

-0.53

 jargon

-0.53

 lawmaker

-0.52

 devil

-0.49

 reference

-0.49

 giveaway

-0.49

 hotline

-0.48

rero

-0.48

POSITIVE LOGITS

byss

0.89

 again

0.76

 thereafter

0.76

Reloaded

0.72

 anew

0.71

Conclusion

0.69

ÃĽ

0.68

Finally

0.67

 resumed

0.66

 finally

0.66

Activations Density 1.280%

information about a person's medical treatment, particularly related to being transported to hospitals for treatment and release

phrases related to medical treatment and recovery events

No Comments

No Known Activations