INDEX

Explanations

references to legal terms, especially related to due process

oai_token-act-pair · gpt-3.5-turbo

references to due process in legal and governmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

qqa

-0.83

oggle

-0.76

arest

-0.71

 Seymour

-0.69

aco

-0.67

arre

-0.66

 Vaugh

-0.66

zzi

-0.65

 Sheep

-0.65

arro

-0.64

POSITIVE LOGITS

 diligence

1.21

giving

0.83

lling

0.80

 consideration

0.79

 scrutiny

0.79

 notice

0.78

gment

0.75

gers

0.75

brance

0.75

jud

0.74

Activations Density 0.026%

references to legal terms, especially related to due process

references to due process in legal and governmental contexts

No Comments

No Known Activations