INDEX

Explanations

punctuation marks that indicate quotes or speech

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

Attribution or source citation

np_acts-logits-general · gemini-2.0-flash

dash or hyphen separators

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 Absicht

-0.43

 monasterio

-0.39

 äusser

-0.39

 disini

-0.39

 Erscheinung

-0.38

 eigentliche

-0.36

 Belastung

-0.36

 ohnehin

-0.36

 originaux

-0.35

 bislang

-0.35

POSITIVE LOGITS

–

1.47

—

1.45

--

1.33

1.32

—

1.20

―

1.16

--

1.10

—

1.09

−

1.09

 ——

1.06

Activations Density 0.330%

punctuation marks that indicate quotes or speech

Attribution or source citation

dash or hyphen separators

No Comments

No Known Activations