INDEX

Explanations

patterns of whitespace and line breaks in structured text data

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

JSON properties and values

np_acts-logits-general · gemini-2.0-flash

structured data keys

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

<?

-0.51

{};

-0.51

Co

-0.51

 comp

-0.51

gu

-0.47

imedia

-0.47

():

-0.45

 Jones

-0.44

[];

-0.44

대

-0.44

POSITIVE LOGITS

+#+#

0.80

 Roskov

0.77

fjspx

0.75

principalColumn

0.74

 Réponses

0.74

+#+

0.73

mybatisplus

0.72

 Référence

0.70

 JpaRepository

0.68

ftagPool

0.67

Activations Density 0.145%

patterns of whitespace and line breaks in structured text data

JSON properties and values

structured data keys

No Comments

No Known Activations