INDEX

Explanations

technology-related terms with a focus on voice assistants and autonomous systems

oai_token-act-pair · gpt-3.5-turbo

terms related to wearable and autonomous technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pite

-0.83

Catholic

-0.79

agall

-0.79

 Sabb

-0.74

ional

-0.73

ewater

-0.72

lishes

-0.72

 adjourn

-0.72

å¥³

-0.71

estones

-0.68

POSITIVE LOGITS

 technology

1.01

 sensors

0.97

 technologies

0.96

earable

0.93

 wearable

0.93

 bots

0.92

 headsets

0.91

Lens

0.91

 prototypes

0.87

 robots

0.86

Activations Density 0.390%

technology-related terms with a focus on voice assistants and autonomous systems

terms related to wearable and autonomous technologies

No Comments

No Known Activations