INDEX

Explanations

phrases related to legal actions, especially overturning decisions or rulings

oai_token-act-pair · gpt-3.5-turbo

instances of the word "overturn" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iatrics

-0.78

artney

-0.71

gil

-0.66

NetMessage

-0.65

azines

-0.64

ebus

-0.63

ickr

-0.61

tern

-0.61

Torrent

-0.61

ART

-0.61

POSITIVE LOGITS

 overturned

0.84

 overturn

0.79

 verdict

0.71

ragon

0.69

uled

0.68

Roe

0.66

uling

0.65

aline

0.63

eering

0.62

 rulings

0.61

Activations Density 0.029%

phrases related to legal actions, especially overturning decisions or rulings

instances of the word "overturn" and its variations

No Comments

No Known Activations