INDEX

Explanations

references to shopping and related items or activities

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

shoplifting or cart theft

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

RetentionPolicy

-0.39

GEBURTSDATUM

-0.37

 Reichen

-0.34

ive

-0.33

isStatic

-0.33

차

-0.32

 leksikon

-0.31

deepEqual

-0.31

Newswire

-0.30

 pied

-0.30

POSITIVE LOGITS

存于互联网档案馆

0.73

 disambiguazione

0.73

 للمعارف

0.69

 shopper

0.66

 ujednoznacz

0.65

 shoppers

0.60

 shopping

0.57

tanleria

0.57

 supermarket

0.56

shopping

0.56

Activations Density 0.113%

references to shopping and related items or activities

shoplifting or cart theft

No Comments

No Known Activations