INDEX

Explanations

references to arrays in programming contexts

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

array or arr

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

="@+

-0.48

GN

-0.45

tagHelperRunner

-0.45

 Kitten

-0.44

layoutControl

-0.44

 Starlight

-0.43

 resourceCulture

-0.43

_->

-0.43

kert

-0.43

credi

-0.42

POSITIVE LOGITS

 ujednoznacz

0.59

NSArray

0.52

########.

0.51

 nakalista

0.51

asList

0.49

Array

0.49

WithMany

0.49

 Lijst

0.48

 disambiguazione

0.48

 IndexPath

0.47

Activations Density 0.012%

references to arrays in programming contexts

array or arr

No Comments

No Known Activations