INDEX

Explanations

legal and regulatory terms

oai_token-act-pair · gpt-3.5-turbo

references to legal concepts and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Bundy

-0.98

GOP

-0.97

Chuck

-0.95

GOP

-0.93

 Chevy

-0.92

 Wichita

-0.90

 Omaha

-0.89

 Hispanic

-0.89

colored

-0.88

 longtime

-0.88

POSITIVE LOGITS

 offences

1.82

 authorised

1.73

 offence

1.63

 licences

1.54

 licence

1.45

 recognised

1.42

 statutory

1.34

 Tribunal

1.33

 recognise

1.33

 organis

1.32

Activations Density 0.711%

legal and regulatory terms

references to legal concepts and frameworks

No Comments

No Known Activations