INDEX

Explanations

legal terms and allegations in a text

oai_token-act-pair · gpt-3.5-turbo

elements related to legal charges and allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 goofy

-1.00

 colorful

-0.93

 fueling

-0.92

 badass

-0.89

 favorites

-0.89

 centers

-0.88

 favorite

-0.87

Enlarge

-0.86

 fueled

-0.83

 someday

-0.82

POSITIVE LOGITS

 appellant

1.39

 Whilst

1.39

 enqu

1.36

 authorised

1.35

 complainant

1.33

 offences

1.31

 Defendant

1.25

 secondly

1.22

 Â£

1.20

 solicitor

1.19

Activations Density 1.325%

legal terms and allegations in a text

elements related to legal charges and allegations

No Comments

No Known Activations