INDEX

Explanations

comments or documentation tags in code

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

Code and markup snippets

np_acts-logits-general · gemini-2.0-flash

JavaScript functions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

gdx

-0.88

 Kett

-0.86

ly

-0.82

FXML

-0.82

POM

-0.81

WebServlet

-0.81

 поло

-0.78

formKey

-0.78

 Exter

-0.77

OrEqualTo

-0.77

POSITIVE LOGITS

1.13

קישורים

0.99

 gră

0.78

-\

0.74

 Galilee

0.73

 alchemist

0.70

 partea

0.70

PAH

0.69

 jScrollPane

0.66

 Danilo

0.65

Activations Density 0.216%

comments or documentation tags in code

Code and markup snippets

JavaScript functions

No Comments

No Known Activations