INDEX

Explanations

references to stores and shopping

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

stores and shopping places

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

SuppressLint

-0.44

 Anexo

-0.37

󠁣

-0.37

 sequence

-0.35

 motion

-0.35

Grath

-0.35

 performed

-0.35

folge

-0.34

amur

-0.33

 ultimately

-0.33

POSITIVE LOGITS

 stores

0.60

 shopping

0.60

 store

0.59

 supermarkets

0.57

 supermarket

0.57

 retailers

0.56

 retailer

0.56

 autorytatywna

0.56

商店

0.56

stores

0.54

Activations Density 0.018%

references to stores and shopping

stores and shopping places

No Comments

No Known Activations