INDEX

Explanations

code structure and function definitions

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

code parsing and serialization

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

 محفوظة

-0.34

şört

-0.33

 lider

-0.33

archiw

-0.33

การ

-0.33

 chỗ

-0.33

AnchorTagHelper

-0.33

 Réponses

-0.32

 Reisen

-0.32

 pagkak

-0.31

POSITIVE LOGITS

ValueStyle

0.70

tagHelperRunner

0.69

endcsname

0.69

OGND

0.68

GEBURTSDATUM

0.63

ſelves

0.61

">//

0.54

MLLoader

0.50

RTGC

0.50

Personensuche

0.48

Activations Density 0.246%

code structure and function definitions

code parsing and serialization

No Comments

No Known Activations