INDEX

Explanations

the structure and components of code annotations and documentation comments

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

in the, three,

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

MigrationBuilder

-0.55

nonatomic

-0.54

醐

-0.49

izante

-0.48

ArgumentParser

-0.42

ISCH

-0.42

ends

-0.42

bread

-0.40

óngase

-0.40

POSITIVE LOGITS

مصادر

0.71

"")

0.71

UnitTesting

0.62

]$}

0.61

 autorytatywna

0.60

""}

0.59

Manbalar

0.58

térature

0.58

 endfor

0.57

ControllerTest

0.57

Activations Density 0.037%

the structure and components of code annotations and documentation comments

Code or special characters

in the, three,

No Comments

No Known Activations