INDEX

Explanations

words related to Motorola devices

oai_token-act-pair · gpt-3.5-turbo

references to specific Motorola phone models and their features

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

elaide

-0.86

tnc

-0.80

istics

-0.76

iments

-0.76

igree

-0.75

ipeg

-0.75

tein

-0.73

 Michaels

-0.70

imental

-0.69

ition

-0.68

POSITIVE LOGITS

GP

1.23

 Moto

0.99

XM

0.92

cycle

0.87

 Maker

0.86

 Mods

0.84

0.82

 Mobility

0.79

åİ

0.78

Maker

0.76

Activations Density 0.039%

words related to Motorola devices

references to specific Motorola phone models and their features

No Comments

No Known Activations