INDEX

Explanations

elements of code related to method definitions and returns

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

Code snippets and signatures

np_acts-logits-general · gemini-2.0-flash

legal documents and code

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

-0.47

posables

-0.47

SPJ

-0.46

NOPQRST

-0.46

 disambiguazione

-0.44

ARIO

-0.43

ikiki

-0.43

限り

-0.43

rsiniz

-0.43

Semif

-0.42

POSITIVE LOGITS

 Arxivat

0.69

)]);

0.65

 GenerationType

0.63

]})

0.61

>--}}

0.59

 RequestMethod

0.57

 doPost

0.55

 دیکھیے

0.55

windowFixed

0.54

Geplaatst

0.54

Activations Density 0.087%

elements of code related to method definitions and returns

Code snippets and signatures

legal documents and code

No Comments

No Known Activations