INDEX

Explanations

references to various locations such as offices, gyms, restaurants, and specific venues

oai_token-act-pair · gpt-3.5-turbo

expressions related to preference or fondness

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

alion

-0.74

Parameters

-0.72

iour

-0.72

 deficiency

-0.70

ptoms

-0.70

attribute

-0.68

 strengthens

-0.68

potion

-0.68

borne

-0.67

umar

-0.67

POSITIVE LOGITS

 Starbucks

1.29

 Macy

1.26

 Oprah

1.22

MTV

1.18

 Playboy

1.16

 Netflix

1.16

 Subway

1.15

 Craigslist

1.15

 Disneyland

1.14

 Hulu

1.13

Activations Density 0.527%

references to various locations such as offices, gyms, restaurants, and specific venues

expressions related to preference or fondness

No Comments

No Known Activations