INDEX

Explanations

programming constructs and elements related to data types and return statements

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

Followed by parameters/fields/labels and their types

np_acts-logits-general · gemini-2.0-flash

code identifiers

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

endphp

-0.74

FunctionFlags

-0.70

LookAnd

-0.68

 utafitiHapana

-0.67

oa̍t

-0.66

HideFlags

-0.64

 autorytatywna

-0.64

 kasarigan

-0.63

 ब्रेकडाउन

-0.62

XmlAccessorType

-0.60

POSITIVE LOGITS

同様に

0.40

 equally

0.39

 similarly

0.37

 wiederum

0.36

同样

0.35

Sa

0.35

 incoming

0.34

 agency

0.34

 furthermore

0.34

 lookout

0.33

Activations Density 0.366%

programming constructs and elements related to data types and return statements

Followed by parameters/fields/labels and their types

code identifiers

No Comments

No Known Activations