INDEX

Explanations

code-related structures and elements, particularly in programming or scripting contexts

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

code and definitions

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

GEBURTSDATUM

-0.71

ValueGeneration

-0.44

">//

-0.41

DockStyle

-0.38

Diweddarwch

-0.37

afficheront

-0.37

jspb

-0.35

 pymysql

-0.35

withIdentifier

-0.35

VolleyError

-0.35

POSITIVE LOGITS

 AssemblyCompany

0.51

ucha

0.49

elancer

0.48

iosis

0.47

 kohdetta

0.47

raim

0.47

ucs

0.47

uolo

0.46

SpringBootTest

0.46

 matéria

0.46

Activations Density 0.016%

code-related structures and elements, particularly in programming or scripting contexts

code and definitions

No Comments

No Known Activations