INDEX

Explanations

programming language syntax and structure, particularly specific keywords and annotations

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

Code, especially related to class definitions

np_acts-logits-general · gemini-2.0-flash

class definitions and object instantiation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 officielles

-0.37

 trails

-0.33

 ویکی‌آمباردا

-0.33

 princesas

-0.32

ConfigureAwait

-0.32

AddHtmlAttribute

-0.31

 испы

-0.31

 dinners

-0.30

 poř

-0.30

 expérimentés

-0.30

POSITIVE LOGITS

 class

1.18

 classe

1.03

class

0.98

 clase

0.98

 classes

0.96

 Class

0.93

classe

0.91

 класс

0.87

 CLASS

0.87

 kelas

0.87

Activations Density 0.249%

programming language syntax and structure, particularly specific keywords and annotations

Code, especially related to class definitions

class definitions and object instantiation

No Comments

No Known Activations