INDEX

Explanations

function-related keywords and programming language syntax

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

Code-related tokens and characters

np_acts-logits-general · gemini-2.0-flash

programming setters and getters

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

withstanding

-1.21

viembre

-0.78

StreetMap

-0.77

Manbalar

-0.76

которые

-0.75

AndView

-0.75

tably

-0.73

alyptus

-0.73

itudinal

-0.70

queous

-0.68

POSITIVE LOGITS

eger

0.67

 ویکی‌پدیا

0.65

CADE

0.59

schung

0.56

 astore

0.55

ˈ

0.55

0.54

adeloupe

0.54

dze

0.53

Activations Density 0.509%

function-related keywords and programming language syntax

Code-related tokens and characters

programming setters and getters

No Comments

No Known Activations