INDEX

Explanations

references to specific artistic works or cultural expressions

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

Italian language

np_acts-logits-general · gemini-2.0-flash

Italian language context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 itself

-0.43

 vPvB

-0.42

"./

-0.41

 doGet

-0.41

 spokesman

-0.41

elu

-0.40

awaiter

-0.40

 Leger

-0.39

 Chwiliwch

-0.39

 keinem

-0.38

POSITIVE LOGITS

la

1.44

il

1.25

0.98

0.97

le

0.90

lo

0.80

 quella

0.77

 quelli

0.75

 quello

0.71

gli

0.70

Activations Density 0.013%

references to specific artistic works or cultural expressions

Italian language

Italian language context

No Comments

No Known Activations