INDEX

Explanations

phrases related to possessive forms of entities

oai_token-act-pair · gpt-3.5-turbo

possessive forms related to institutions or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

holes

-0.78

flix

-0.77

 Unsure

-0.77

Quantity

-0.73

amiya

-0.73

 Controls

-0.71

Pak

-0.71

amed

-0.70

sson

-0.70

aly

-0.67

POSITIVE LOGITS

own

1.21

 namesake

0.96

 newest

0.89

 flagship

0.85

 inability

0.83

ELF

0.83

 finances

0.83

 initials

0.82

 trademark

0.81

 predecessor

0.81

Activations Density 0.100%

phrases related to possessive forms of entities

possessive forms related to institutions or entities

No Comments

No Known Activations