INDEX

Explanations

descriptions related to architectural structures

oai_token-act-pair · gpt-3.5-turbo

references to physical structures or environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Recommend

-0.91

src

-0.88

 Regarding

-0.79

 Attend

-0.78

ASON

-0.76

quickShipAvailable

-0.74

relation

-0.73

instance

-0.72

ibliography

-0.72

Minor

-0.71

POSITIVE LOGITS

 sleek

1.46

 towering

1.32

 lush

1.32

 slender

1.28

 shadowy

1.26

 chilly

1.25

 fiery

1.25

 rugged

1.24

 slick

1.24

 dazzling

1.24

Activations Density 1.115%

descriptions related to architectural structures

references to physical structures or environments

No Comments

No Known Activations