INDEX

Explanations

function definitions and calls related to setting values in a data structure

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

"set" appearing in code

np_acts-logits-general · gemini-2.0-flash

programming code setters

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

charCodeAt

-0.47

idUser

-0.47

hideLoading

-0.46

 irreparable

-0.46

cplusplus

-0.46

 Flanagan

-0.45

 indexOf

-0.45

forChild

-0.45

lastModified

-0.45

انتهای

-0.44

POSITIVE LOGITS

set

1.88

set

1.81

Set

1.67

Set

1.67

SET

1.42

SET

1.38

 sets

1.22

 Sets

1.16

セット

1.15

 ſet

1.12

Activations Density 0.125%

function definitions and calls related to setting values in a data structure

"set" appearing in code

programming code setters

No Comments

No Known Activations