INDEX

Explanations

references to events and specific entities related to individuals and their activities

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

family and children

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

SBATCH

-0.63

 surla

-0.60

 препратки

-0.59

DeleteBehavior

-0.59

 estekak

-0.56

 snippetHide

-0.54

Cyfeiriadau

-0.53

OGND

-0.52

Diweddarwch

-0.51

 utafitiHapana

-0.51

POSITIVE LOGITS

+#+#

0.33

یدم

0.33

sements

0.33

system

0.31

singleton

0.30

<strong>

0.30

 tils

0.30

 cheminée

0.30

dienste

0.30

sys

0.30

Activations Density 0.233%

references to events and specific entities related to individuals and their activities

family and children

No Comments

No Known Activations