INDEX

Explanations

mathematical symbols and notation related to functions and variables

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

mathematical notation and code

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

 <>",

-0.60

 comuniques

-0.60

 surla

-0.58

UrlResolution

-0.57

 Theſe

-0.55

 سكانية

-0.54

存于互联网档案馆

-0.54

原始内容存档于

-0.52

aarrggbb

-0.52

 initComponents

-0.52

POSITIVE LOGITS

fromnode

0.35

ParallelGroup

0.33

 rând

0.32

 correction

0.32

webElementXpaths

0.30

 resourceCulture

0.29

 schimb

0.29

 Labour

0.29

lab

0.29

 rank

0.29

Activations Density 1.065%

mathematical symbols and notation related to functions and variables

mathematical notation and code

No Comments

No Known Activations