INDEX

Explanations

code and programming terms, especially in C++ and potentially related to Facebook's JNI or React Native.

oai_token-act-pair · gemini-2.0-flash

C++ namespace delimiters

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

say "::"

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

Not in Any Lists

No Comments

Negative Logits

Становништво

-0.52

 biologie

-0.48

-0.47

vantaged

-0.45

 Gouverneur

-0.43

—

-0.42

исленность

-0.42

typeorm

-0.40

 виправивши

-0.40

jfree

-0.39

POSITIVE LOGITS

::

1.77

::

1.59

::_

1.13

::__

1.05

:::

1.05

::$

1.02

::::

0.99

:::

0.92

>::

0.87

::{

0.80

Activations Density 1.521%

code and programming terms, especially in C++ and potentially related to Facebook's JNI or React Native.

C++ namespace delimiters

say "::"

No Comments

No Known Activations