INDEX

Explanations

technical details related to image processing or feature extraction methodologies

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

'])->

-0.55

 endregion

-0.54

 Taktlose

-0.52

 safer

-0.51

tanooga

-0.51

mold

-0.51

neté

-0.50

randir

-0.50

 EconPapers

-0.50

Viitteet

-0.48

POSITIVE LOGITS

 neither

0.62

 никаких

0.61

 unmodified

0.61

 without

0.59

 ника

0.57

 никакого

0.57

 aucune

0.56

initComponents

0.56

 nessuna

0.56

 hiçbir

0.55

Activations Density 0.625%

technical details related to image processing or feature extraction methodologies

No Comments

No Known Activations