INDEX

Explanations

instances of legal or regulatory provisions or rules mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "provisions."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Wr

-0.69

Jr

-0.68

Marie

-0.66

zzy

-0.65

 clicked

-0.65

fuck

-0.64

 Rage

-0.64

 comeback

-0.63

roid

-0.60

alpha

-0.60

POSITIVE LOGITS

 provisions

3.56

 provision

2.04

 clauses

1.80

 prohibitions

1.57

 amendments

1.50

 protections

1.48

 statutes

1.47

 loopholes

1.46

 safeguards

1.39

 requirements

1.38

Activations Density 0.011%

instances of legal or regulatory provisions or rules mentioned in a text

instances of the word "provisions."

No Comments

No Known Activations