INDEX

Explanations

references to first instances or commands in procedural or operational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 समीक्षक

-0.67

 ujednoznacz

-0.61

 disambiguazione

-0.60

GOTREF

-0.60

Datuak

-0.58

 intptr

-0.56

InlineData

-0.55

 estimés

-0.52

]+=

-0.51

autaire

-0.51

POSITIVE LOGITS

ImageContext

0.54

 lightest

0.52

matchCondition

0.52

GraphicsUnit

0.51

 usually

0.51

Hozzáférés

0.50

 dianteiro

0.50

selectedItem

0.50

assigns

0.49

getActiveSheet

0.48

Activations Density 0.729%

references to first instances or commands in procedural or operational contexts

No Comments

No Known Activations