INDEX

Explanations

references to voice-activated virtual assistants like Siri and Kinect

oai_token-act-pair · gpt-3.5-turbo

terms related to voice-activated virtual assistants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rity

-0.71

fs

-0.67

POS

-0.65

hog

-0.65

tg

-0.65

ersen

-0.63

raft

-0.62

itted

-0.62

umbai

-0.61

rug

-0.61

POSITIVE LOGITS

 Siri

1.28

 Cortana

1.11

 Bots

0.77

 speaker

0.73

ADRA

0.70

 Philips

0.68

Voice

0.68

 Jarvis

0.68

 iCloud

0.67

Kit

0.67

Activations Density 0.021%

references to voice-activated virtual assistants like Siri and Kinect

terms related to voice-activated virtual assistants

No Comments

No Known Activations