INDEX

Explanations

keywords related to automobile brands, models, and features

oai_token-act-pair · gpt-3.5-turbo

information related to automobiles 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 besie

-0.80

adelphia

-0.79

 Patreon

-0.76

iannopoulos

-0.75

 defund

-0.73

tsy

-0.72

 Psychiat

-0.72

 Dice

-0.71

PNG

-0.71

arantine

-0.71

POSITIVE LOGITS

 Mazda

1.86

 Toyota

1.82

 Chevrolet

1.81

BMW

1.76

 Honda

1.75

 Nissan

1.73

 Porsche

1.73

 automakers

1.70

 Volkswagen

1.69

 sedan

1.65

Activations Density 0.537%

keywords related to automobile brands, models, and features

information related to automobiles and their features

No Comments

No Known Activations