INDEX

Explanations

mentions of regulations and laws related to various topics or industries

oai_token-act-pair · gpt-3.5-turbo

phrases related to laws and regulations

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

sense

-0.83

appointed

-0.81

DragonMagazine

-0.81

auntlet

-0.77

nces

-0.74

 Strateg

-0.74

amara

-0.74

context

-0.73

Dispatch

-0.73

vind

-0.71

POSITIVE LOGITS

 imports

1.18

 interstate

1.16

 greenhouse

1.04

 exports

0.98

 recreational

0.96

 cigarettes

0.95

 imported

0.95

 commerce

0.94

 commercial

0.93

 importing

0.90

Activations Density 0.228%

mentions of regulations and laws related to various topics or industries

phrases related to laws and regulations

No Comments

No Known Activations