INDEX

Explanations

instances of legal contexts, laws, and regulations

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal regulations and their applicability

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ£

-0.76

bernatorial

-0.70

STAR

-0.70

andowski

-0.68

aukee

-0.68

ILLE

-0.66

 Poles

-0.64

-0.62

ospace

-0.61

DragonMagazine

-0.61

POSITIVE LOGITS

cutting

1.05

lining

1.05

pins

1.02

lying

0.97

graduate

0.96

writing

0.92

lined

0.90

dogs

0.89

neath

0.88

ħĭ

0.88

Activations Density 0.047%

instances of legal contexts, laws, and regulations

phrases related to legal regulations and their applicability

No Comments

No Known Activations