INDEX

Explanations

numerical data and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.76

aarrggbb

-0.68

GEBURTSDATUM

-0.63

OGND

-0.62

 مشين

-0.60

WebServlet

-0.60

 pinulongan

-0.60

UrlResolution

-0.59

numerusform

-0.58

原始内容存档于

-0.56

POSITIVE LOGITS

 Print

0.39

Print

0.37

 Peak

0.35

Tracking

0.35

Cod

0.35

 Flags

0.35

 Gläub

0.34

lamos

0.34

 State

0.34

 smoking

0.34

Activations Density 1.023%

numerical data and identifiers

No Comments

No Known Activations