INDEX

Explanations

programming constructs related to control flow

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

Ends code snippets or blocks of code

np_acts-logits-general · gemini-2.0-flash

code declarations and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

évaluateur

-0.67

ConstraintMaker

-0.66

+:+

-0.58

󠁢

-0.57

 للمعارف

-0.56

 JpaRepository

-0.56

帖最后由

-0.56

GraphicsUnit

-0.54

 transfieras

-0.54

 Chwiliwch

-0.54

POSITIVE LOGITS

 defaultstate

0.48

死的

0.32

 Call

0.31

graphique

0.31

 Class

0.30

IDENTAL

0.30

ReactDOM

0.30

 declaration

0.29

 Construction

0.29

Exam

0.28

Activations Density 0.338%

programming constructs related to control flow

Ends code snippets or blocks of code

code declarations and definitions

No Comments

No Known Activations