INDEX

Explanations

references to tools and equipment necessary for specific tasks or activities

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

purchase

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MockMvc

-0.48

 język

-0.48

 consom

-0.46

 ennemi

-0.43

 langage

-0.41

pæ

-0.41

setMaximum

-0.40

 gotas

-0.39

 accordo

-0.39

 Gebet

-0.39

POSITIVE LOGITS

 springfox

0.42

पया

0.40

 equipment

0.40

 disambiguazione

0.39

 outright

0.39

 lenker

0.38

 Ausrüstung

0.37

 ddelweddau

0.36

 purchased

0.36

imetsu

0.35

Activations Density 0.025%

references to tools and equipment necessary for specific tasks or activities

purchase

No Comments

No Known Activations