INDEX

Explanations

mentions of legislative actions or proposals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating proposed changes or amendments in legislation

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

 Passion

-0.69

UGH

-0.69

rete

-0.68

 Divinity

-0.65

living

-0.63

ive

-0.62

\/

-0.61

ovo

-0.61

peak

-0.61

 foss

-0.60

POSITIVE LOGITS

 prohibits

1.36

 restricts

1.27

 forbids

1.25

 regulates

1.24

 governs

1.23

 allows

1.22

 prevents

1.21

 protects

1.19

 imposes

1.17

 eliminates

1.13

Activations Density 0.103%

mentions of legislative actions or proposals

phrases indicating proposed changes or amendments in legislation

No Comments

No Known Activations