INDEX

Explanations

programming loops and control structures

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

loop constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Paglinawan

-0.73

GOTREF

-0.63

 viewDidLoad

-0.59

setVerticalGroup

-0.59

Hentet

-0.54

migrationBuilder

-0.54

aarrggbb

-0.54

featureID

-0.54

styleType

-0.54

şört

-0.52

POSITIVE LOGITS

InstrumentedTest

0.37

tagPool

0.36

توض

0.36

+#+#

0.35

Vorlage

0.31

pun

0.31

kirch

0.31

BB

0.30

 Trois

0.29

ArrowToggle

0.29

Activations Density 0.037%

programming loops and control structures

loop constructs

No Comments

No Known Activations