INDEX

Explanations

programming-related keywords and operations

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

Code snippets or programming-related text

np_acts-logits-general · gemini-2.0-flash

function calls and code constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

genodigd

-0.65

liceerd

-0.60

存于互联网档案馆

-0.54

="@+

-0.54

 Autorisations

-0.52

 nahilalakip

-0.52

}{@

-0.51

 Chwiliwch

-0.51

 propOrder

-0.49

 Autorizaciones

-0.49

POSITIVE LOGITS

PostMapping

0.38

ty

0.37

 trial

0.37

En

0.37

Feel

0.37

 Whittaker

0.37

+:+

0.36

 exercises

0.36

 lesson

0.36

Activity

0.36

Activations Density 0.093%

programming-related keywords and operations

Code snippets or programming-related text

function calls and code constructs

No Comments

No Known Activations