INDEX

Explanations

code related to API definitions and requirements

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

Code-related tokens such as "pub," "fn," and "impl."

np_acts-logits-general · gemini-2.0-flash

Rust pub fn

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

+#+#

-0.59

省市镇

-0.58

IntoConstraints

-0.57

Ծանոթ

-0.56

phazard

-0.55

 Topping

-0.54

enterOuterAlt

-0.54

vese

-0.53

 snippetHide

-0.52

 فہرست

-0.52

POSITIVE LOGITS

pub

0.73

fn

0.61

nonatomic

0.60

#[

0.59

fn

0.57

pub

0.55

delwed

0.52

 impl

0.49

 fact

0.48

 Clínica

0.48

Activations Density 0.082%

code related to API definitions and requirements

Code-related tokens such as "pub," "fn," and "impl."

Rust pub fn

No Comments

No Known Activations