INDEX

Explanations

important keywords or notifications within a text, such as "Notify," "For," "Please," "Added," "More specifically," and "What."

oai_token-act-pair · gpt-3.5-turbo

directives and procedural language

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

''

-0.80

.","

-0.72

.</

-0.67

 ..."

-0.66

 thereto

-0.64

 âĢ¦"

-0.62

 downt

-0.61

)</

-0.60

Ù

-0.60

 stud

-0.60

POSITIVE LOGITS

resa

1.08

 Conclusion

1.08

ibliography

1.00

notations

0.94

odore

0.89

tymology

0.89

 Example

0.88

roma

0.87

 Contents

0.85

chieve

0.85

Activations Density 0.581%

important keywords or notifications within a text, such as "Notify," "For," "Please," "Added," "More specifically," and "What."

directives and procedural language

No Comments

No Known Activations