INDEX

Explanations

references to parameters and identifiers commonly used in programming and configuration contexts

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

Code snippets or programming-related text

np_acts-logits-general · gemini-2.0-flash

code assignment or data structure

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

<bos>

-0.50

--

-0.46

abspath

-0.45

 énergé

-0.45

Personendaten

-0.44

 automatiques

-0.44

 eccl

-0.43

haviour

-0.42

стка

-0.41

the

-0.40

POSITIVE LOGITS

=>

1.18

 للاسماء

1.00

=>

0.90

ArgsConstructor

0.89

 JpaRepository

0.88

"=>

0.84

⇒

0.83

]=>

0.81

 resourceCulture

0.79

 propOrder

0.79

Activations Density 0.297%

references to parameters and identifiers commonly used in programming and configuration contexts

Code snippets or programming-related text

code assignment or data structure

No Comments

No Known Activations