INDEX

Explanations

phrases related to privacy policies and user information usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

+#+#

-0.70

ISupport

-0.62

HasIndex

-0.62

ToMany

-0.60

 Pante

-0.60

IBOutlet

-0.59

 Hashtable

-0.59

findpost

-0.59

 Wicidata

-0.59

setPreferred

-0.59

POSITIVE LOGITS

 sauvages

0.53

utory

0.53

 peindre

0.51

 positifs

0.50

 beroep

0.50

 flotante

0.50

 nommé

0.49

 fédé

0.49

 loisirs

0.48

 étrangères

0.48

Activations Density 0.238%

phrases related to privacy policies and user information usage

No Comments

No Known Activations