INDEX

Explanations

references to method documentation and code structure in programming languages

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

Code comments with annotations and parameters

np_acts-logits-general · gemini-2.0-flash

code and markup

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

 يتيمه

-0.64

-------------</

-0.62

RegressionTest

-0.58

exitRule

-0.53

 Palestina

-0.51

 Perſ

-0.51

Aktualisiert

-0.50

 Meksiku

-0.50

duate

-0.49

delwed

-0.48

POSITIVE LOGITS

cshtml

0.49

 convite

0.39

MathML

0.38

yntaxException

0.37

</th>

0.36

Bigr

0.36

Zw

0.35

liness

0.35

blurRadius

0.35

sow

0.35

Activations Density 0.065%

references to method documentation and code structure in programming languages

Code comments with annotations and parameters

code and markup

No Comments

No Known Activations