INDEX

Explanations

terms related to legal compliance and regulation

oai_token-act-pair · gpt-3.5-turbo

references to compliance with regulations and laws

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iewicz

-1.05

asp

-0.82

cloth

-0.78

bern

-0.76

utra

-0.75

bold

-0.73

ãĥ£

-0.70

ulton

-0.69

 Roses

-0.68

arnaev

-0.67

POSITIVE LOGITS

 compliance

1.12

 Compliance

1.06

compliance

0.96

ibilities

0.92

 enforcement

0.89

 monitoring

0.86

 violations

0.86

 requirements

0.83

encies

0.82

 regimes

0.82

Activations Density 0.019%

terms related to legal compliance and regulation

references to compliance with regulations and laws

No Comments

No Known Activations