INDEX

Explanations

syntax elements related to data structures and conditions in programming

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

Code, variable, or class names

np_acts-logits-general · gemini-2.0-flash

directional node

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

 مشين

-0.91

AnchorStyles

-0.85

EndGlobalSection

-0.83

InjectAttribute

-0.81

parsedMessage

-0.77

tvguidetime

-0.77

LookAnd

-0.76

IVEREF

-0.70

 kasarigan

-0.63

GEBURTSDATUM

-0.62

POSITIVE LOGITS

 houſe

0.70

 Diſ

0.67

 ſmall

0.65

 reaſon

0.63

 Anſ

0.62

wiſe

0.62

 Majefty

0.62

 ſeveral

0.61

 Reſ

0.61

 juſ

0.61

Activations Density 0.121%

syntax elements related to data structures and conditions in programming

Code, variable, or class names

directional node

No Comments

No Known Activations