INDEX

Explanations

phrases related to grouping or categorization

oai_token-act-pair · gpt-3.5-turbo

references to groups in various contexts, particularly related to classifications or competitions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shire

-0.78

wards

-0.71

DAY

-0.69

issance

-0.67

LV

-0.66

 Dame

-0.65

 Latest

-0.63

Bloomberg

-0.63

Adv

-0.63

SIGN

-0.63

POSITIVE LOGITS

emonium

1.04

roups

0.98

think

0.92

ativity

0.91

ings

0.91

arettes

0.88

 sizes

0.87

 members

0.87

mates

0.87

leader

0.86

Activations Density 0.053%

phrases related to grouping or categorization

references to groups in various contexts, particularly related to classifications or competitions

No Comments

No Known Activations