INDEX

Explanations

key indicators such as important punctuation and structural elements

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

Punctuation followed by specific words

np_acts-logits-general · gemini-2.0-flash

below, here, or similar indicators

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

Искәрмәләр

-0.78

Билгалдахарш

-0.78

AsUp

-0.72

Idem

-0.71

 Савезне

-0.69

 ComVisible

-0.66

Jereo

-0.64

Erreferentziak

-0.63

 Idem

-0.61

 createSprite

-0.59

POSITIVE LOGITS

 Below

1.70

Below

1.67

 below

1.62

 Here

1.43

 here

1.42

Here

1.33

 voici

1.27

below

1.27

 berikut

1.24

下面

1.22

Activations Density 0.219%

key indicators such as important punctuation and structural elements

Punctuation followed by specific words

below, here, or similar indicators

No Comments

No Known Activations