INDEX

Explanations

programming terminology related to factories and function handling in code

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

factory or generator

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

-0.40

woners

-0.37

OwnProperty

-0.36

ResponseWriter

-0.35

 übernehmen

-0.34

cheid

-0.34

ouſ

-0.34

Hear

-0.33

擂

-0.33

Життєпис

-0.33

POSITIVE LOGITS

ConstraintMaker

0.65

WebElementEntity

0.62

RTSN

0.58

IndentedString

0.56

Supplier

0.56

MLLoader

0.54

Itoa

0.54

 EconPapers

0.54

 linkovi

0.52

 '\\;'

0.51

Activations Density 0.030%

programming terminology related to factories and function handling in code

factory or generator

No Comments

No Known Activations