INDEX

Explanations

programming-related commands and properties

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

Code snippets with colons and brackets

np_acts-logits-general · gemini-2.0-flash

`:` notation

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

 Sarmiento

-0.65

tauan

-0.54

 Pingback

-0.53

modb

-0.52

⁠

-0.51

—"

-0.50

 Warlock

-0.50

 Candace

-0.49

 Bautista

-0.49

POSITIVE LOGITS

::

1.54

.:

1.48

1.47

(:

1.37

::

1.34

:::

1.26

:(

1.26

,:

1.24

：

1.23

/:

1.23

Activations Density 0.575%

programming-related commands and properties

Code snippets with colons and brackets

`:` notation

No Comments

No Known Activations