INDEX

Explanations

phrases related to legal actions or law enforcement

oai_token-act-pair · gpt-3.5-turbo

occurrences of punctuation, particularly periods and question marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 torpedo

-0.91

 mushroom

-0.87

 recognised

-0.83

 sausage

-0.82

 rubbish

-0.81

 loft

-0.80

bom

-0.80

 organised

-0.79

 arte

-0.78

 compound

-0.78

POSITIVE LOGITS

âĢ

2.27

âľ

1.40

âĢł

1.39

ãĢ

1.28

 âĢ

1.26

âĻ

1.24

âĹ

1.22

âĹı

1.22

âģ

1.19

âĨ

1.18

Activations Density 0.323%

phrases related to legal actions or law enforcement

occurrences of punctuation, particularly periods and question marks

No Comments

No Known Activations