INDEX

Explanations

words related to weight, measurement, and statistics

oai_token-act-pair · gpt-3.5-turbo

terms related to weights and obesity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

AIDS

-0.81

 Noir

-0.73

BLE

-0.73

ades

-0.72

Dub

-0.71

ilk

-0.70

uve

-0.69

 Imperium

-0.69

 Defenders

-0.68

ffe

-0.67

POSITIVE LOGITS

 weights

1.25

 weighted

1.14

ighed

1.03

weights

1.01

 weigh

0.98

 heavier

0.92

 heaviest

0.91

 weighing

0.89

 overweight

0.88

weight

0.85

Activations Density 0.012%

words related to weight, measurement, and statistics

terms related to weights and obesity

No Comments

No Known Activations