INDEX

Explanations

references to products and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Мексичка

-0.93

 Normdatei

-0.92

 twine

-0.92

 HasFactory

-0.90

=$?

-0.85

 Constitucional

-0.84

 <>",

-0.84

 AIAA

-0.83

<!--[

-0.83

 BSEB

-0.82

POSITIVE LOGITS

 products

1.72

 product

1.64

 Product

1.36

 Products

1.35

 PRODUCT

1.33

product

1.31

 producto

1.30

Products

1.28

products

1.26

Product

1.25

Activations Density 0.039%

references to products and related terms

No Comments

No Known Activations