INDEX

Explanations

statistical references and methods related to data analysis

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

Sentences that start with discourse markers

np_acts-logits-general · gemini-2.0-flash

summarizing conclusions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

enderror

-0.56

 يتيمه

-0.56

rungsseite

-0.54

 للمعارف

-0.51

fromnode

-0.43

 disambiguazione

-0.41

المشاركات

-0.41

sizeCache

-0.40

Werdegang

-0.40

Lähteet

-0.38

POSITIVE LOGITS

 Altogether

0.56

AndEndTag

0.50

Overall

0.48

 Outro

0.47

 Overall

0.47

 препратки

0.47

Corporate

0.46

 overall

0.45

Cid

0.45

ntax

0.45

Activations Density 0.369%

statistical references and methods related to data analysis

Sentences that start with discourse markers

summarizing conclusions

No Comments

No Known Activations