INDEX

Explanations

attributes related to GPU device properties or parameters

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

code snippets and programming syntax

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

richTextPanel

-0.65

printStackTrace

-0.63

GOTREF

-0.62

 schoenen

-0.59

 ſol

-0.57

parsedMessage

-0.57

 mijne

-0.56

 ſtate

-0.56

genodigd

-0.56

ſelf

-0.56

POSITIVE LOGITS

Aiheesta

0.39

0.37

 Bent

0.37

 Wiener

0.35

(!

0.35

（

0.34

（

0.34

jsxFileName

0.34

⠀

0.34

ldots

0.34

Activations Density 0.040%

attributes related to GPU device properties or parameters

code snippets and programming syntax

No Comments

No Known Activations