INDEX

Explanations

words related to legal actions, specifically indictments

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to legal indictments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atan

-0.96

birth

-0.83

hare

-0.69

istic

-0.69

 Nightmares

-0.69

 Likes

-0.69

 lear

-0.69

population

-0.68

 Rapt

-0.67

 Bees

-0.66

POSITIVE LOGITS

 indictment

1.29

 indict

1.21

 indicted

1.20

eering

0.97

 proceedings

0.95

 subpoen

0.92

 warrant

0.91

 summ

0.90

 unse

0.90

ments

0.89

Activations Density 0.043%

words related to legal actions, specifically indictments

terms and phrases related to legal indictments

No Comments

No Known Activations