INDEX

Explanations

the keyword `new`, often followed by a data type or function name, suggesting it's identifying object instantiation or new object creation in code snippets.

oai_token-act-pair · gemini-2.0-flash

instances of creating new objects or files

np_token-act-pair-logits · gpt-4o-mini

new

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

TestingModule

-0.52

 InputDecoration

-0.52

TestBed

-0.50

ServiceTest

-0.49

ctest

-0.48

 tasche

-0.48

tease

-0.45

啶

-0.44

 esteja

-0.44

oteo

-0.44

POSITIVE LOGITS

 يتيمه

0.70

 صوتيه

0.66

ScopeManager

0.62

DockStyle

0.61

béco

0.60

MemoryWarning

0.59

")[

0.59

 فريبيس

0.58

Rhestr

0.58

 للمعارف

0.58

Activations Density 0.310%

the keyword `new`, often followed by a data type or function name, suggesting it's identifying object instantiation or new object creation in code snippets.

instances of creating new objects or files

new

No Known Activations

the keyword `new`, often followed by a data type or function name, suggesting it's identifying object instantiation or new object creation in code snippets.

instances of creating new objects or files

new

No Known Activations