INDEX

Explanations

keywords and access modifiers related to programming constructs

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

<start_of_turn>user usage

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

^[

-0.30

RTGC

-0.27

 externi

-0.27

ERT

-0.26

 pata

-0.26

キラ

-0.25

 उप

-0.25

 exclusive

-0.25

 exclusivo

-0.25

ContentAlignment

-0.25

POSITIVE LOGITS

 autorytatywna

0.94

:✨

0.80

 Мексичка

0.79

featureID

0.78

OGND

0.74

 jScrollPane

0.73

 ویکی‌پدیای

0.73

SourceChecksum

0.72

 AssemblyTitle

0.66

 AssemblyCompany

0.66

Activations Density 0.049%

keywords and access modifiers related to programming constructs

<start_of_turn>user usage

No Comments

No Known Activations

keywords and access modifiers related to programming constructs

<start_of_turn>user usage

No Comments

No Known Activations