INDEX

Explanations

phrases related to laws, regulations, and political structures

oai_token-act-pair · gpt-3.5-turbo

the phrase "In" used at the beginning of sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 refreshed

-0.63

 unlocks

-0.62

 lodged

-0.62

 spoil

-0.61

 babe

-0.61

 looms

-0.60

 unemploy

-0.59

 entertained

-0.58

 combatants

-0.57

 trave

-0.57

POSITIVE LOGITS

herent

1.35

 contrast

1.29

 addition

1.27

sofar

1.26

 spite

1.26

ventory

1.22

 fact

1.20

cluding

1.20

adequ

1.16

advert

1.15

Activations Density 0.165%

phrases related to laws, regulations, and political structures

the phrase "In" used at the beginning of sentences

No Comments

No Known Activations