INDEX

Explanations

programming language constructs related to views or methods involved in rendering content

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

Code, file paths, and software related terms

np_acts-logits-general · gemini-2.0-flash

technical and multilingual terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 noqa

-0.60

CloseOperation

-0.60

 OnInit

-0.53

templateUrl

-0.52

migrationBuilder

-0.49

下载附件

-0.49

vermectin

-0.48

providedIn

-0.47

 villaggio

-0.47

Javadoc

-0.47

POSITIVE LOGITS

 Wikimedijinoj

0.62

wnież

0.59

Viitteet

0.58

Сылтамалар

0.56

 propOrder

0.55

fjspx

0.55

 internetowa

0.53

 haka

0.52

niko

0.51

новниш

0.50

Activations Density 0.055%

programming language constructs related to views or methods involved in rendering content

Code, file paths, and software related terms

technical and multilingual terms

No Comments

No Known Activations