INDEX

Explanations

conjunctions and references to collaborative efforts in various contexts

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

after conjunctions and punctuation

np_acts-logits-general · gemini-2.0-flash

categories and items

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

 âmes

-0.38

เพ

-0.32

wal

-0.31

 meilleurs

-0.30

is

-0.28

but

-0.28

®

-0.28

 اینکه

-0.28

</h6>

-0.27

 Mayor

-0.27

POSITIVE LOGITS

 gadgets

0.68

niſſe

0.66

IsMutable

0.59

poň

0.58

族館

0.58

ulae

0.57

 exchangers

0.57

ArrowToggle

0.57

 summaries

0.57

 combos

0.57

Activations Density 0.481%

conjunctions and references to collaborative efforts in various contexts

after conjunctions and punctuation

categories and items

No Comments

No Known Activations