INDEX

Explanations

references to titles, positions, or roles in contexts involving events or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

허

-0.52

CppMethod

-0.49

 HttpStatusCode

-0.48

 biên

-0.48

vlo

-0.47

 Retrieves

-0.47

 pasi

-0.47

 intptr

-0.46

SerializedSize

-0.46

 clínicos

-0.46

POSITIVE LOGITS

__":

0.73

 civilian

0.67

 sports

0.61

انيف

0.61

ofür

0.60

 beginnetje

0.58

styleType

0.54

 Extragalactic

0.54

CardContent

0.54

 contextLoads

0.53

Activations Density 1.662%

references to titles, positions, or roles in contexts involving events or organizations

No Comments

No Known Activations