INDEX

Explanations

references to programming language concepts, specifically queryable data and data handling functions

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

programming and medicine

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

DeleteMapping

-0.33

 Puedes

-0.30

Cal

-0.30

 grade

-0.30

 שוליים

-0.30

 BoxFit

-0.26

']->

-0.26

'])){

-0.26

dostęp

-0.26

 Grade

-0.26

POSITIVE LOGITS

toCharArray

1.52

DispatchToProps

1.50

ActionCreators

1.29

fromCharCode

1.13

Recycler

0.85

Queryable

0.82

 AssemblyTitle

0.78

 AssemblyVersion

0.75

 onCreateView

0.73

pulseira

0.73

Activations Density 0.000%

references to programming language concepts, specifically queryable data and data handling functions

programming and medicine

No Comments

No Known Activations