INDEX

Explanations

digits or numbers embedded in text

oai_token-act-pair · gpt-3.5-turbo

specific identifiers and codes, likely related to a classification or categorization system

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

OFF

-0.80

 metic

-0.75

COM

-0.71

 GREEN

-0.68

FOX

-0.66

ALE

-0.66

HA

-0.66

 EDITION

-0.66

DIS

-0.65

 MUST

-0.64

POSITIVE LOGITS

1.43

1.42

1.41

1.39

1.35

1.34

1.33

1.32

Activations Density 0.291%

digits or numbers embedded in text

specific identifiers and codes, likely related to a classification or categorization system

No Comments

No Known Activations