INDEX

Explanations

mathematical constructs related to ultra-filters and topological spaces in functional analysis

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

in I

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

EDEFAULT

-0.67

 utafitiHapana

-0.59

 vroeger

-0.53

 uſed

-0.53

 henvisninger

-0.52

 للاسماء

-0.51

 Formerly

-0.50

kuuta

-0.49

 يتيمه

-0.48

optionalTypeArgs

-0.48

POSITIVE LOGITS

UnknownFieldSet

0.36

getMenuInflater

0.36

قایناق‌لار

0.36

Климат

0.35

 MainAxisSize

0.34

getClassLoader

0.33

 varsa

0.32

enschappelijke

0.32

ことから

0.31

łach

0.30

Activations Density 0.431%

mathematical constructs related to ultra-filters and topological spaces in functional analysis

in I

No Comments

No Known Activations