INDEX

Explanations

references to "Mas" or related terms, often in medical or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 benne

-0.49

Ỉ

-0.49

 volna

-0.47

 demais

-0.46

Leaks

-0.45

 personlig

-0.45

 firm

-0.45

Solución

-0.45

elesen

-0.43

 linken

-0.43

POSITIVE LOGITS

 ModelExpression

0.86

Mas

0.84

Mas

0.77

ConstraintMaker

0.72

mas

0.71

WireFormatLite

0.70

ChildScrollView

0.70

 Roskov

0.69

 intptr

0.68

enumii

0.67

Activations Density 0.195%

references to "Mas" or related terms, often in medical or technical contexts

No Comments

No Known Activations