INDEX

Explanations

references to personal ownership or guidance

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

your best guide or ally

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 disambiguazione

-0.54

AntiForgeryToken

-0.48

 stances

-0.47

 للاسماء

-0.47

новниш

-0.46

ⓧ

-0.45

 financeira

-0.44

liceerd

-0.44

rungsseite

-0.43

 uważ

-0.43

POSITIVE LOGITS

 guide

0.52

 faſt

0.50

 dependable

0.47

 reliable

0.47

guide

0.47

Solución

0.47

 friendly

0.47

 ally

0.44

 Anſ

0.44

 friend

0.43

Activations Density 0.008%

references to personal ownership or guidance

your best guide or ally

No Comments

No Known Activations