INDEX

Explanations

code related to C++ namespaces and classes

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

C++ namespaces and types

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

存于互联网档案馆

-0.61

tagHelperRunner

-0.50

InputBorder

-0.48

ГЛА

-0.47

 فريبيس

-0.46

DECREF

-0.46

INFL

-0.46

parsedMessage

-0.45

ỡng

-0.45

MVP

-0.45

POSITIVE LOGITS

::

1.38

::

0.87

:::

0.87

>::

0.86

(::

0.83

::$

0.76

::{

0.71

>::

0.68

:::

0.64

__::

0.62

Activations Density 0.020%

code related to C++ namespaces and classes

C++ namespaces and types

No Comments

No Known Activations