INDEX

Explanations

specific constructs and expressions used in programming and code-related contexts

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

technical identifiers and code constructs

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

RegressionTest

-0.73

setVerticalGroup

-0.67

 tartalomajánló

-0.51

IndentedString

-0.49

 noDo

-0.47

 Drapeau

-0.44

 ویکی‌پدی

-0.44

KURZBESCHREIBUNG

-0.44

例文帳に追加

-0.43

########.

-0.42

POSITIVE LOGITS

Rhestr

0.57

VIAF

0.50

 يتيمه

0.49

 Administrativna

0.48

TargetException

0.46

ValueStyle

0.44

 konk

0.43

 NUKAT

0.43

)\}$

0.41

httphttps

0.41

Activations Density 0.017%

specific constructs and expressions used in programming and code-related contexts

technical identifiers and code constructs

No Comments

No Known Activations

specific constructs and expressions used in programming and code-related contexts

technical identifiers and code constructs

No Comments

No Known Activations