INDEX

Explanations

questions and inquiries about specific details or clarifications

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

asking questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

+#+

-0.44

 JpaRepository

-0.44

 saurait

-0.41

UnusedPrivate

-0.41

posedge

-0.40

 pamię

-0.39

SuppressMessage

-0.39

\{\\

-0.38

bbene

-0.38

 NUKAT

-0.37

POSITIVE LOGITS

➯

0.53

GEBURTSDATUM

0.51

Rok

0.47

:✨

0.46

 compar

0.44

навли

0.43

الغ

0.42

fav

0.42

WithIOException

0.41

报

0.41

Activations Density 0.062%

questions and inquiries about specific details or clarifications

asking questions

No Comments

No Known Activations