INDEX

Explanations

organizational names and titles

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

organizations and institutions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Infórmanos

-0.36

 Exacts

-0.35

 moeili

-0.33

kháu

-0.31

 <=",

-0.31

abstractmethod

-0.30

 harder

-0.30

حياته

-0.30

 ApiException

-0.28

 niezbęd

-0.27

POSITIVE LOGITS

 Jurisdiction

0.62

 plufieurs

0.60

 Existence

0.58

 fusca

0.57

ſelf

0.57

KommentareTeilen

0.57

 Verſ

0.57

 ſeinen

0.56

 carina

0.55

 Resonance

0.55

Activations Density 0.031%

organizational names and titles

organizations and institutions

No Comments

No Known Activations