INDEX

Explanations

references to Java code and auto-generated methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nonUne

-0.77

 betweenstory

-0.74

ConstraintMaker

-0.67

IntoConstraints

-0.64

OGND

-0.63

principalColumn

-0.63

verifyException

-0.62

المكان

-0.61

routeProvider

-0.59

WithMany

-0.58

POSITIVE LOGITS

 تضيفلها

0.57

Diwedd

0.53

 JADX

0.47

 tartalomajánló

0.46

 ويكيپيديا

0.41

 snippetHide

0.41

Eksterne

0.40

Segoe

0.38

 incomplète

0.37

<thead>

0.36

Activations Density 0.735%

references to Java code and auto-generated methods

No Comments

No Known Activations