INDEX

Explanations

code related to database interactions or operations

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

Programming code snippets

np_acts-logits-general · gemini-2.0-flash

code snippets and programming terms

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

rungsseite

-0.74

SharedCtor

-0.69

 мәкал

-0.68

 gyhoeddwyd

-0.65

 Савезне

-0.64

hyrchwyd

-0.62

:✨

-0.61

Jeografia

-0.60

expandindo

-0.59

Personensuche

-0.57

POSITIVE LOGITS

 Crespo

0.45

bildet

0.42

 AspNetCore

0.41

 Moser

0.40

śni

0.40

 regras

0.39

tilha

0.39

 Metzger

0.38

 protocolos

0.38

ทอง

0.38

Activations Density 0.608%

code related to database interactions or operations

Programming code snippets

code snippets and programming terms

No Comments

No Known Activations