INDEX

Explanations

mentions of the word "Alexa" or related to Amazon's Alexa voice assistant

oai_token-act-pair · gpt-3.5-turbo

references to the voice assistant Alexa and associated developers or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ileged

-0.84

dayName

-0.79

çļ

-0.72

 Serpent

-0.71

het

-0.68

 Prot

-0.68

COP

-0.68

 condol

-0.67

âī

-0.67

 ration

-0.66

POSITIVE LOGITS

 Alexa

2.48

 Foley

2.19

 Caldwell

1.77

 Mayer

1.45

 Cortana

1.16

 Baxter

1.13

 Baghd

1.10

 Elias

1.04

 Lowell

1.04

 McKay

1.03

Activations Density 0.047%

mentions of the word "Alexa" or related to Amazon's Alexa voice assistant

references to the voice assistant Alexa and associated developers or features

No Comments

No Known Activations