INDEX

Explanations

instances of comments in code

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

Code comments or headers

np_acts-logits-general · gemini-2.0-flash

start of block comments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.62

lase

-0.52

werker

-0.50

 Horv

-0.49

 RECOMMEND

-0.48

ulico

-0.48

 RECOMEND

-0.48

grä

-0.48

}}^{(

-0.47

 DEFEND

-0.46

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.47

/*

0.42

Hochspringen

0.41

httphttps

0.39

writeField

0.37

帖最后由

0.37

});*/

0.36

évaluateur

0.36

/*

0.35

 protoimpl

0.35

Activations Density 0.271%

instances of comments in code

Code comments or headers

start of block comments

No Comments

No Known Activations

instances of comments in code

Code comments or headers

start of block comments

No Comments

No Known Activations